Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1084 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1314. Min Range: -6.1314
Max Act: 6.1314. Min Act: -0.1700
Data Index: 952097 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1314. Min Range: -6.1314
Max Act: 6.0689. Min Act: -0.1700
Data Index: 1975444 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9751. Min Act: -0.1700
Data Index: 558483 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9751. Min Act: -0.1700
Data Index: 8010692 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9126. Min Act: -0.1700
Data Index: 5751143 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9439. Min Act: -0.1700
Data Index: 6862634 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9439. Min Act: -0.1700
Data Index: 6978667 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9126. Min Act: -0.1700
Data Index: 3265317 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8814. Min Act: -0.1700
Data Index: 8339022 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8814. Min Act: -0.1700
Data Index: 5506501 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8501. Min Act: -0.1700
Data Index: 3192708 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8814. Min Act: -0.1700
Data Index: 5466010 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8814. Min Act: -0.1700
Data Index: 6920687 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.9126. Min Act: -0.1700
Data Index: 6089844 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7341496 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8189. Min Act: -0.1700
Data Index: 2744556 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8501. Min Act: -0.1700
Data Index: 4261828 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8501. Min Act: -0.1700
Data Index: 743471 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8501. Min Act: -0.1700
Data Index: 4729652 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1314. Min Range: -6.1314
Max Act: 5.8501. Min Act: -0.1700
Data Index: 5470051 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19