Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5094 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.9997. Min Act: -0.1700
Data Index: 6144993 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.9215. Min Act: -0.1700
Data Index: 3176645 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8746. Min Act: -0.1700
Data Index: 1774941 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.9059. Min Act: -0.1700
Data Index: 262532 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8746. Min Act: -0.1700
Data Index: 2427309 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8590. Min Act: -0.1700
Data Index: 1398414 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8590. Min Act: -0.1700
Data Index: 1597289 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8277. Min Act: -0.1700
Data Index: 4577983 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8277. Min Act: -0.1700
Data Index: 6938953 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8121. Min Act: -0.1700
Data Index: 4577985 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1913849 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7964. Min Act: -0.1700
Data Index: 3968917 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7964. Min Act: -0.1700
Data Index: 4577984 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7808. Min Act: -0.1700
Data Index: 155379 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7651. Min Act: -0.1700
Data Index: 2166921 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7495. Min Act: -0.1700
Data Index: 7077841 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7495. Min Act: -0.1700
Data Index: 221462 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7182. Min Act: -0.1700
Data Index: 2533967 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7339. Min Act: -0.1700
Data Index: 7436737 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9997. Min Range: -3.9997
Max Act: 3.7182. Min Act: -0.1700
Data Index: 2067089 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19