Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5992 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2112. Min Range: -6.2112
Max Act: 6.2112. Min Act: -0.1700
Data Index: 1031975 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.9925. Min Act: -0.1700
Data Index: 8383944 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.9612. Min Act: -0.1700
Data Index: 4544124 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.9612. Min Act: -0.1700
Data Index: 6967719 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.9300. Min Act: -0.1700
Data Index: 1395186 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8987. Min Act: -0.1700
Data Index: 4860595 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8675. Min Act: -0.1700
Data Index: 817866 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8675. Min Act: -0.1700
Data Index: 6654820 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8675. Min Act: -0.1700
Data Index: 5381345 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8675. Min Act: -0.1700
Data Index: 6353496 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8675. Min Act: -0.1700
Data Index: 5302470 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8675. Min Act: -0.1700
Data Index: 5531398 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8362. Min Act: -0.1700
Data Index: 5661613 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8050. Min Act: -0.1700
Data Index: 4936469 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8362. Min Act: -0.1700
Data Index: 2248454 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8050. Min Act: -0.1700
Data Index: 6716183 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7737. Min Act: -0.1700
Data Index: 8501431 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8050. Min Act: -0.1700
Data Index: 2204730 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7737. Min Act: -0.1700
Data Index: 3378438 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7737. Min Act: -0.1700
Data Index: 4944605 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19