Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.2823. Min Act: -0.1700
Data Index: 7743154 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.2510. Min Act: -0.1700
Data Index: 671737 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.2510. Min Act: -0.1700
Data Index: 6070791 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.2510. Min Act: -0.1700
Data Index: 2736272 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.2198. Min Act: -0.1700
Data Index: 720812 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.2510. Min Act: -0.1700
Data Index: 6187763 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1885. Min Act: -0.1700
Data Index: 7167500 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1885. Min Act: -0.1700
Data Index: 7491314 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1885. Min Act: -0.1700
Data Index: 4870637 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1573. Min Act: -0.1700
Data Index: 3156410 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1573. Min Act: -0.1700
Data Index: 6488899 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1260. Min Act: -0.1700
Data Index: 2933285 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1573. Min Act: -0.1700
Data Index: 6767521 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1573. Min Act: -0.1700
Data Index: 7541552 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1260. Min Act: -0.1700
Data Index: 3664022 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1260. Min Act: -0.1700
Data Index: 4287971 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1260. Min Act: -0.1700
Data Index: 8515049 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1260. Min Act: -0.1700
Data Index: 7516270 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.1260. Min Act: -0.1700
Data Index: 7095239 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2823. Min Range: -4.2823
Max Act: 4.0948. Min Act: -0.1700
Data Index: 5523267 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19