Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.9344. Min Act: -0.1700
Data Index: 6274966 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.7469. Min Act: -0.1700
Data Index: 2676343 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.7156. Min Act: -0.1700
Data Index: 4257533 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.6844. Min Act: -0.1700
Data Index: 5084513 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.6531. Min Act: -0.1700
Data Index: 709231 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.6844. Min Act: -0.1700
Data Index: 1338570 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.6844. Min Act: -0.1700
Data Index: 6896840 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.6844. Min Act: -0.1700
Data Index: 5012477 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.6219. Min Act: -0.1700
Data Index: 6146217 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.5906. Min Act: -0.1700
Data Index: 1679787 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.5594. Min Act: -0.1700
Data Index: 4370307 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.5281. Min Act: -0.1700
Data Index: 261435 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4969. Min Act: -0.1700
Data Index: 2649024 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4656. Min Act: -0.1700
Data Index: 4828882 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4656. Min Act: -0.1700
Data Index: 6533291 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4656. Min Act: -0.1700
Data Index: 7264995 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4344. Min Act: -0.1700
Data Index: 4392097 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4344. Min Act: -0.1700
Data Index: 7164653 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4344. Min Act: -0.1700
Data Index: 5879771 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9344. Min Range: -5.9344
Max Act: 5.4344. Min Act: -0.1700
Data Index: 4927631 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19