Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.8371. Min Act: -0.1700
Data Index: 7173773 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.7121. Min Act: -0.1700
Data Index: 4483576 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.6183. Min Act: -0.1700
Data Index: 331813 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.6183. Min Act: -0.1700
Data Index: 3057445 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.4933. Min Act: -0.1700
Data Index: 1660165 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.4621. Min Act: -0.1700
Data Index: 7237733 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.4621. Min Act: -0.1700
Data Index: 2079997 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.4308. Min Act: -0.1700
Data Index: 8658162 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.4308. Min Act: -0.1700
Data Index: 7573535 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3996. Min Act: -0.1700
Data Index: 8235560 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3996. Min Act: -0.1700
Data Index: 6919163 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3996. Min Act: -0.1700
Data Index: 3222212 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3683. Min Act: -0.1700
Data Index: 6673373 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3683. Min Act: -0.1700
Data Index: 2961378 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3683. Min Act: -0.1700
Data Index: 6553192 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3371. Min Act: -0.1700
Data Index: 7839534 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3371. Min Act: -0.1700
Data Index: 6870836 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.3058. Min Act: -0.1700
Data Index: 8739881 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.2746. Min Act: -0.1700
Data Index: 4311760 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8371. Min Range: -6.8371
Max Act: 6.2746. Min Act: -0.1700
Data Index: 3011964 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19