Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2282 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.3669. Min Act: -0.1700
Data Index: 3393824 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2885. Min Act: -0.1700
Data Index: 8127773 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2414. Min Act: -0.1700
Data Index: 6731127 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2571. Min Act: -0.1700
Data Index: 8812515 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2414. Min Act: -0.1700
Data Index: 6887062 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2414. Min Act: -0.1700
Data Index: 3270304 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2414. Min Act: -0.1700
Data Index: 1910093 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2256. Min Act: -0.1700
Data Index: 7449551 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2256. Min Act: -0.1700
Data Index: 2353227 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2256. Min Act: -0.1700
Data Index: 6440150 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2256. Min Act: -0.1700
Data Index: 5731250 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2256. Min Act: -0.1700
Data Index: 3597466 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2256. Min Act: -0.1700
Data Index: 2922315 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.2099. Min Act: -0.1700
Data Index: 6669961 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.1942. Min Act: -0.1700
Data Index: 6337765 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.1942. Min Act: -0.1700
Data Index: 6254086 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.1785. Min Act: -0.1700
Data Index: 3698729 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.1785. Min Act: -0.1700
Data Index: 4537686 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.1785. Min Act: -0.1700
Data Index: 2492308 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3669. Min Range: -3.3669
Max Act: 3.1627. Min Act: -0.1700
Data Index: 5872283 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19