Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.2979. Min Act: -0.1700
Data Index: 854651 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1104. Min Act: -0.1700
Data Index: 6071862 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1104. Min Act: -0.1700
Data Index: 3313136 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0791. Min Act: -0.1700
Data Index: 6917466 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0791. Min Act: -0.1700
Data Index: 854656 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9541. Min Act: -0.1700
Data Index: 6117444 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9228. Min Act: -0.1700
Data Index: 2415850 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9854. Min Act: -0.1700
Data Index: 4054577 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9228. Min Act: -0.1700
Data Index: 4642827 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9228. Min Act: -0.1700
Data Index: 586263 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9228. Min Act: -0.1700
Data Index: 7664982 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8603. Min Act: -0.1700
Data Index: 2253459 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8916. Min Act: -0.1700
Data Index: 6667320 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.7978. Min Act: -0.1700
Data Index: 3565790 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8603. Min Act: -0.1700
Data Index: 6526382 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8916. Min Act: -0.1700
Data Index: 2814676 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8916. Min Act: -0.1700
Data Index: 7243831 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9228. Min Act: -0.1700
Data Index: 3948410 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8916. Min Act: -0.1700
Data Index: 845867 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.8916. Min Act: -0.1700
Data Index: 4844421 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19