Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 308 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.7390. Min Act: -0.1700
Data Index: 2697837 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.6765. Min Act: -0.1700
Data Index: 7481481 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.6608. Min Act: -0.1700
Data Index: 8641406 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.5513. Min Act: -0.1700
Data Index: 7237820 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.5356. Min Act: -0.1700
Data Index: 6328250 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.5199. Min Act: -0.1700
Data Index: 1132210 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.4573. Min Act: -0.1700
Data Index: 5043965 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.4103. Min Act: -0.1700
Data Index: 1166682 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.4103. Min Act: -0.1700
Data Index: 5486879 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3789. Min Act: -0.1700
Data Index: 8687754 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3632. Min Act: -0.1700
Data Index: 4525268 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3475. Min Act: -0.1700
Data Index: 8127333 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3632. Min Act: -0.1700
Data Index: 2762413 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3632. Min Act: -0.1700
Data Index: 639221 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3475. Min Act: -0.1700
Data Index: 7416713 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3318. Min Act: -0.1700
Data Index: 6355547 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3475. Min Act: -0.1700
Data Index: 6539850 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3475. Min Act: -0.1700
Data Index: 4663555 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3475. Min Act: -0.1700
Data Index: 5799831 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7390. Min Range: -3.7390
Max Act: 3.3475. Min Act: -0.1700
Data Index: 1822121 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19