Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.9223. Min Act: -0.1700
Data Index: 8683214 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.7660. Min Act: -0.1700
Data Index: 5689440 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1572325 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.7660. Min Act: -0.1700
Data Index: 7931638 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.7035. Min Act: -0.1700
Data Index: 3295677 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.7035. Min Act: -0.1700
Data Index: 551144 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6723. Min Act: -0.1700
Data Index: 6958242 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.7035. Min Act: -0.1700
Data Index: 7931637 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6723. Min Act: -0.1700
Data Index: 8802970 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6723. Min Act: -0.1700
Data Index: 8801400 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6723. Min Act: -0.1700
Data Index: 1436864 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6723. Min Act: -0.1700
Data Index: 5143914 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6723. Min Act: -0.1700
Data Index: 2881483 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6410. Min Act: -0.1700
Data Index: 4449947 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6410. Min Act: -0.1700
Data Index: 118810 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6098. Min Act: -0.1700
Data Index: 3340112 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6098. Min Act: -0.1700
Data Index: 5067201 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.6098. Min Act: -0.1700
Data Index: 3391075 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.5785. Min Act: -0.1700
Data Index: 428105 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9223. Min Range: -5.9223
Max Act: 5.5785. Min Act: -0.1700
Data Index: 2446082 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19