Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.9133. Min Act: -0.1700
Data Index: 6188305 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.5383. Min Act: -0.1700
Data Index: 7413065 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.4758. Min Act: -0.1700
Data Index: 8248555 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.4133. Min Act: -0.1700
Data Index: 6526649 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.1008. Min Act: -0.1700
Data Index: 4064995 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.1008. Min Act: -0.1700
Data Index: 1099968 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9133. Min Range: -10.9133
Max Act: 10.1008. Min Act: -0.1700
Data Index: 5382616 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.9758. Min Act: -0.1700
Data Index: 2742582 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.9758. Min Act: -0.1700
Data Index: 4184462 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.9758. Min Act: -0.1700
Data Index: 3140953 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.9133. Min Act: -0.1700
Data Index: 2689999 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.8508. Min Act: -0.1700
Data Index: 8108752 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.8508. Min Act: -0.1700
Data Index: 4250289 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.7883. Min Act: -0.1700
Data Index: 2751271 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.6633. Min Act: -0.1700
Data Index: 3632966 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.7258. Min Act: -0.1700
Data Index: 6769347 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.7258. Min Act: -0.1700
Data Index: 4961624 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.5383. Min Act: -0.1700
Data Index: 6916575 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.5383. Min Act: -0.1693
Data Index: 3083878 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9133. Min Range: -10.9133
Max Act: 9.6008. Min Act: -0.1700
Data Index: 438079 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19