Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5335 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0009. Min Range: -6.0009
Max Act: 6.0009. Min Act: -0.1700
Data Index: 8725353 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0009. Min Range: -6.0009
Max Act: 6.0009. Min Act: -0.1700
Data Index: 7422756 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.9696. Min Act: -0.1700
Data Index: 2190384 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.9384. Min Act: -0.1700
Data Index: 327768 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.9384. Min Act: -0.1700
Data Index: 6891061 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.8759. Min Act: -0.1700
Data Index: 4616909 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.8446. Min Act: -0.1700
Data Index: 6936028 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.8446. Min Act: -0.1700
Data Index: 1922418 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.8134. Min Act: -0.1700
Data Index: 2254616 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.8134. Min Act: -0.1700
Data Index: 3270068 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7509. Min Act: -0.1700
Data Index: 2686871 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7509. Min Act: -0.1700
Data Index: 960811 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7821. Min Act: -0.1700
Data Index: 6841594 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7509. Min Act: -0.1700
Data Index: 2224410 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7196. Min Act: -0.1700
Data Index: 240318 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7196. Min Act: -0.1700
Data Index: 8090959 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.7196. Min Act: -0.1700
Data Index: 163651 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.6571. Min Act: -0.1700
Data Index: 1786749 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.6571. Min Act: -0.1700
Data Index: 1532809 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0009. Min Range: -6.0009
Max Act: 5.5946. Min Act: -0.1700
Data Index: 1284634 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19