Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.6963. Min Act: -0.1700
Data Index: 838652 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.6025. Min Act: -0.1700
Data Index: 2983986 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5712. Min Act: -0.1700
Data Index: 7859947 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5398. Min Act: -0.1700
Data Index: 7707317 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5398. Min Act: -0.1700
Data Index: 1083483 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5398. Min Act: -0.1700
Data Index: 3815763 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5242. Min Act: -0.1700
Data Index: 6619535 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5242. Min Act: -0.1700
Data Index: 4648787 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5242. Min Act: -0.1700
Data Index: 7444375 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4929. Min Act: -0.1700
Data Index: 1652320 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.5085. Min Act: -0.1700
Data Index: 190105 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4929. Min Act: -0.1700
Data Index: 4679389 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4615. Min Act: -0.1700
Data Index: 4610978 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4615. Min Act: -0.1700
Data Index: 5188358 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4772. Min Act: -0.1700
Data Index: 2000920 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4459. Min Act: -0.1700
Data Index: 1092076 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4459. Min Act: -0.1700
Data Index: 1301290 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4302. Min Act: -0.1700
Data Index: 3885267 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4145. Min Act: -0.1700
Data Index: 6157192 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6963. Min Range: -3.6963
Max Act: 3.4145. Min Act: -0.1700
Data Index: 2902974 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19