Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3746 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.7454. Min Act: -0.1700
Data Index: 1651995 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.5892. Min Act: -0.1700
Data Index: 6761318 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.5267. Min Act: -0.1700
Data Index: 220840 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.5267. Min Act: -0.1700
Data Index: 8573645 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.4642. Min Act: -0.1700
Data Index: 6534664 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.4642. Min Act: -0.1700
Data Index: 7924374 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.4329. Min Act: -0.1700
Data Index: 2617308 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.3704. Min Act: -0.1700
Data Index: 3608999 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.3079. Min Act: -0.1700
Data Index: 3457879 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.2767. Min Act: -0.1700
Data Index: 5645672 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.2767. Min Act: -0.1700
Data Index: 1081845 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.2142. Min Act: -0.1700
Data Index: 3377841 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.2142. Min Act: -0.1700
Data Index: 86654 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.2142. Min Act: -0.1700
Data Index: 7776171 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7454. Min Range: -7.7454
Max Act: 7.1829. Min Act: -0.1700
Data Index: 2677589 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7454. Min Range: -7.7454
Max Act: 6.9954. Min Act: -0.1700
Data Index: 3597880 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7454. Min Range: -7.7454
Max Act: 6.9954. Min Act: -0.1700
Data Index: 7240380 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7454. Min Range: -7.7454
Max Act: 6.9954. Min Act: -0.1700
Data Index: 5849848 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7454. Min Range: -7.7454
Max Act: 6.9954. Min Act: -0.1700
Data Index: 4074222 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7454. Min Range: -7.7454
Max Act: 6.9329. Min Act: -0.1700
Data Index: 4838961 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19