Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1188 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.7524. Min Act: -0.1700
Data Index: 2504680 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2668. Min Act: -0.1700
Data Index: 5703732 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2039. Min Act: -0.1700
Data Index: 4232420 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2039. Min Act: -0.1700
Data Index: 3189656 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2354. Min Act: -0.1700
Data Index: 4640440 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2196. Min Act: -0.1700
Data Index: 7972991 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2039. Min Act: -0.1700
Data Index: 5904952 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.2039. Min Act: -0.1700
Data Index: 7897291 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1882. Min Act: -0.1700
Data Index: 8342773 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1882. Min Act: -0.1700
Data Index: 7934889 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1882. Min Act: -0.1700
Data Index: 328594 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1567. Min Act: -0.1700
Data Index: 1490141 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1725. Min Act: -0.1700
Data Index: 5876449 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1567. Min Act: -0.1700
Data Index: 5606786 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1567. Min Act: -0.1700
Data Index: 3685328 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1567. Min Act: -0.1700
Data Index: 6675647 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1410. Min Act: -0.1700
Data Index: 6127326 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1567. Min Act: -0.1700
Data Index: 5217097 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1252. Min Act: -0.1700
Data Index: 7031468 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7524. Min Range: -3.7524
Max Act: 3.1567. Min Act: -0.1700
Data Index: 2514902 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19