Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5000 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 2421200 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.4191. Min Act: -0.1700
Data Index: 4835786 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.3878. Min Act: -0.1700
Data Index: 2484140 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.3566. Min Act: -0.1700
Data Index: 7243864 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4115597 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.3566. Min Act: -0.1700
Data Index: 50699 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.3253. Min Act: -0.1700
Data Index: 580708 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.3253. Min Act: -0.1700
Data Index: 2484138 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2941. Min Act: -0.1700
Data Index: 5841902 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2941. Min Act: -0.1700
Data Index: 4085424 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2941. Min Act: -0.1700
Data Index: 1432855 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2628. Min Act: -0.1699
Data Index: 8069962 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2628. Min Act: -0.1700
Data Index: 1360814 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2628. Min Act: -0.1700
Data Index: 1231335 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2316. Min Act: -0.1700
Data Index: 6688196 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2316. Min Act: -0.1700
Data Index: 6828019 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2316. Min Act: -0.1700
Data Index: 7052223 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2003. Min Act: -0.1700
Data Index: 4821484 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2316. Min Act: -0.1700
Data Index: 4352435 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4191. Min Range: -6.4191
Max Act: 6.2316. Min Act: -0.1700
Data Index: 7245689 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19