Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.8281. Min Act: -0.1700
Data Index: 8321353 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.5781. Min Act: -0.1700
Data Index: 1939122 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.6094. Min Act: -0.1700
Data Index: 8194877 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.5156. Min Act: -0.1700
Data Index: 8078028 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.4531. Min Act: -0.1700
Data Index: 3386767 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.4219. Min Act: -0.1700
Data Index: 1814485 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.4219. Min Act: -0.1700
Data Index: 2661294 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.4219. Min Act: -0.1700
Data Index: 6802329 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.3281. Min Act: -0.1700
Data Index: 2486325 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.3281. Min Act: -0.1700
Data Index: 7377566 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2969. Min Act: -0.1700
Data Index: 5372856 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2656. Min Act: -0.1700
Data Index: 7909785 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2656. Min Act: -0.1700
Data Index: 4455724 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2344. Min Act: -0.1700
Data Index: 2096409 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7870309 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2031. Min Act: -0.1700
Data Index: 6553972 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2031. Min Act: -0.1700
Data Index: 1835620 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.2031. Min Act: -0.1700
Data Index: 7851680 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.1719. Min Act: -0.1700
Data Index: 6085865 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8281. Min Range: -6.8281
Max Act: 6.1719. Min Act: -0.1700
Data Index: 4925618 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19