Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.9276. Min Act: -0.1700
Data Index: 8134951 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.5839. Min Act: -0.1700
Data Index: 2382689 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.5839. Min Act: -0.1700
Data Index: 7483023 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.5526. Min Act: -0.1700
Data Index: 5717506 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.5839. Min Act: -0.1700
Data Index: 5047027 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4901. Min Act: -0.1700
Data Index: 3925971 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4589. Min Act: -0.1700
Data Index: 4550928 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4589. Min Act: -0.1700
Data Index: 6110642 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4589. Min Act: -0.1700
Data Index: 8450366 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4589. Min Act: -0.1700
Data Index: 7217726 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4589. Min Act: -0.1700
Data Index: 4088752 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4589. Min Act: -0.1700
Data Index: 5305556 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4276. Min Act: -0.1700
Data Index: 412631 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.4276. Min Act: -0.1700
Data Index: 7554843 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.3964. Min Act: -0.1700
Data Index: 3337344 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.3964. Min Act: -0.1700
Data Index: 7421926 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.3651. Min Act: -0.1700
Data Index: 926658 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.3339. Min Act: -0.1700
Data Index: 455381 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.3339. Min Act: -0.1700
Data Index: 555471 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9276. Min Range: -6.9276
Max Act: 6.3339. Min Act: -0.1700
Data Index: 2568756 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19