Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 15.7129. Min Range: -15.7129
Max Act: 15.7129. Min Act: -0.1700
Data Index: 1825652 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.7129. Min Range: -15.7129
Max Act: 15.2129. Min Act: -0.1700
Data Index: 101755 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.7129. Min Range: -15.7129
Max Act: 15.1504. Min Act: -0.1700
Data Index: 7004243 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.7129. Min Range: -15.7129
Max Act: 15.1504. Min Act: -0.1700
Data Index: 8207874 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.7129. Min Range: -15.7129
Max Act: 15.0254. Min Act: -0.1700
Data Index: 4483044 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.9004. Min Act: -0.1700
Data Index: 799574 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.9004. Min Act: -0.1700
Data Index: 7808146 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.9004. Min Act: -0.1700
Data Index: 7808142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.8379. Min Act: -0.1700
Data Index: 8720347 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.8379. Min Act: -0.1700
Data Index: 147133 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.7129. Min Act: -0.1700
Data Index: 3717809 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.6504. Min Act: -0.1700
Data Index: 7214658 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.6504. Min Act: -0.1700
Data Index: 6108311 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.4004. Min Act: -0.1700
Data Index: 7808145 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.4004. Min Act: -0.1700
Data Index: 4652726 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.4004. Min Act: -0.1700
Data Index: 2376267 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.3379. Min Act: -0.1700
Data Index: 2548064 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.3379. Min Act: -0.1700
Data Index: 2566056 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.3379. Min Act: -0.1700
Data Index: 147132 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.7129. Min Range: -15.7129
Max Act: 14.3379. Min Act: -0.1700
Data Index: 7126592 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19