Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5654 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.6490. Min Act: -0.1700
Data Index: 6251576 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.5865. Min Act: -0.1700
Data Index: 4861279 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.5865. Min Act: -0.1700
Data Index: 1195086 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.5552. Min Act: -0.1700
Data Index: 2775588 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.5552. Min Act: -0.1700
Data Index: 1143773 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.5240. Min Act: -0.1700
Data Index: 3345246 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4927. Min Act: -0.1700
Data Index: 3082428 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4927. Min Act: -0.1700
Data Index: 7312987 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1784057 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4615. Min Act: -0.1700
Data Index: 3134044 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4302. Min Act: -0.1700
Data Index: 613066 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4615. Min Act: -0.1700
Data Index: 6800876 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4302. Min Act: -0.1700
Data Index: 7871021 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4302. Min Act: -0.1700
Data Index: 7627690 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4302. Min Act: -0.1700
Data Index: 6099758 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4302. Min Act: -0.1700
Data Index: 6593137 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.3990. Min Act: -0.1700
Data Index: 4507692 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.3990. Min Act: -0.1700
Data Index: 8038711 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.3990. Min Act: -0.1700
Data Index: 1928322 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6490. Min Range: -5.6490
Max Act: 5.4302. Min Act: -0.1700
Data Index: 6497317 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19