Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.5239. Min Act: -0.1700
Data Index: 3285021 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.4614. Min Act: -0.1700
Data Index: 399777 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.3677. Min Act: -0.1700
Data Index: 4705990 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1810130 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.3364. Min Act: -0.1700
Data Index: 8126647 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.2739. Min Act: -0.1700
Data Index: 5105419 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.2427. Min Act: -0.1700
Data Index: 4904975 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.2739. Min Act: -0.1700
Data Index: 5786788 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.2114. Min Act: -0.1700
Data Index: 6265548 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.1489. Min Act: -0.1700
Data Index: 4996615 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.0864. Min Act: -0.1700
Data Index: 7256408 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.0552. Min Act: -0.1700
Data Index: 6235015 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.0239. Min Act: -0.1700
Data Index: 4188194 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5239. Min Range: -6.5239
Max Act: 6.0239. Min Act: -0.1700
Data Index: 5248351 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5239. Min Range: -6.5239
Max Act: 5.9927. Min Act: -0.1700
Data Index: 5627379 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5239. Min Range: -6.5239
Max Act: 5.9927. Min Act: -0.1700
Data Index: 3324739 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5239. Min Range: -6.5239
Max Act: 5.9927. Min Act: -0.1700
Data Index: 1338033 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5239. Min Range: -6.5239
Max Act: 5.9927. Min Act: -0.1700
Data Index: 8227007 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5239. Min Range: -6.5239
Max Act: 5.9927. Min Act: -0.1700
Data Index: 5827032 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5239. Min Range: -6.5239
Max Act: 5.9927. Min Act: -0.1700
Data Index: 3047471 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19