Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1830 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.7085. Min Act: -0.1700
Data Index: 7357295 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6765. Min Act: -0.1700
Data Index: 567226 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6765. Min Act: -0.1700
Data Index: 4381513 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6444. Min Act: -0.1700
Data Index: 3785171 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6444. Min Act: -0.1700
Data Index: 3642312 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6123. Min Act: -0.1700
Data Index: 6413547 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6284. Min Act: -0.1700
Data Index: 3845016 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6123. Min Act: -0.1700
Data Index: 2314091 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6123. Min Act: -0.1700
Data Index: 4022619 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6123. Min Act: -0.1700
Data Index: 6565133 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5962. Min Act: -0.1700
Data Index: 7169090 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.6123. Min Act: -0.1700
Data Index: 7064960 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5801. Min Act: -0.1700
Data Index: 1061721 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5801. Min Act: -0.1700
Data Index: 7553471 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5801. Min Act: -0.1700
Data Index: 4562725 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5640. Min Act: -0.1700
Data Index: 1028508 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5640. Min Act: -0.1700
Data Index: 7993556 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5640. Min Act: -0.1700
Data Index: 2569427 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5640. Min Act: -0.1700
Data Index: 8267102 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7085. Min Range: -2.7085
Max Act: 2.5478. Min Act: -0.1700
Data Index: 3104417 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19