Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5071 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2371. Min Act: -0.1700
Data Index: 4264813 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1121. Min Act: -0.1700
Data Index: 6450490 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 8778108 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 7343859 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9559. Min Act: -0.1700
Data Index: 4485426 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9246. Min Act: -0.1700
Data Index: 7646870 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9246. Min Act: -0.1700
Data Index: 4538504 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9246. Min Act: -0.1700
Data Index: 4288412 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 2780542 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8621. Min Act: -0.1700
Data Index: 441248 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8621. Min Act: -0.1700
Data Index: 775561 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8934. Min Act: -0.1700
Data Index: 2413580 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8309. Min Act: -0.1700
Data Index: 5029807 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8309. Min Act: -0.1700
Data Index: 1371766 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4034804 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.8309. Min Act: -0.1700
Data Index: 7250980 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.7996. Min Act: -0.1700
Data Index: 2495837 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.7996. Min Act: -0.1700
Data Index: 8123947 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.7996. Min Act: -0.1700
Data Index: 1483427 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.7684. Min Act: -0.1700
Data Index: 3127061 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19