Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.9765. Min Act: -0.1700
Data Index: 609466 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.9453. Min Act: -0.1700
Data Index: 4498791 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.9453. Min Act: -0.1700
Data Index: 4874630 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.8515. Min Act: -0.1700
Data Index: 834343 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.8203. Min Act: -0.1700
Data Index: 7327987 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7890. Min Act: -0.1700
Data Index: 5705678 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7578. Min Act: -0.1700
Data Index: 1922503 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7578. Min Act: -0.1700
Data Index: 7894031 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7578. Min Act: -0.1700
Data Index: 5474490 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7578. Min Act: -0.1700
Data Index: 2111346 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7578. Min Act: -0.1700
Data Index: 7076431 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7265. Min Act: -0.1700
Data Index: 191155 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.7265. Min Act: -0.1700
Data Index: 6149380 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6640. Min Act: -0.1700
Data Index: 8808996 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6640. Min Act: -0.1700
Data Index: 8505807 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6640. Min Act: -0.1700
Data Index: 3858601 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6640. Min Act: -0.1700
Data Index: 326926 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6953. Min Act: -0.1700
Data Index: 5124654 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6640. Min Act: -0.1700
Data Index: 8033941 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9765. Min Range: -5.9765
Max Act: 5.6328. Min Act: -0.1700
Data Index: 2659840 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19