Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5758 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.5426. Min Act: -0.1700
Data Index: 2658973 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.4801. Min Act: -0.1700
Data Index: 7976759 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.5113. Min Act: -0.1700
Data Index: 8043916 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.3863. Min Act: -0.1700
Data Index: 4654135 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.3863. Min Act: -0.1700
Data Index: 4250195 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.3551. Min Act: -0.1700
Data Index: 2993935 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.3551. Min Act: -0.1700
Data Index: 4992835 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.3551. Min Act: -0.1700
Data Index: 2213271 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.3238. Min Act: -0.1700
Data Index: 5616374 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2926. Min Act: -0.1700
Data Index: 3253279 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2613. Min Act: -0.1700
Data Index: 5304628 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2613. Min Act: -0.1700
Data Index: 3280184 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2926. Min Act: -0.1700
Data Index: 5549198 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2613. Min Act: -0.1700
Data Index: 437582 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2613. Min Act: -0.1700
Data Index: 437581 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2926. Min Act: -0.1700
Data Index: 2882574 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2301. Min Act: -0.1700
Data Index: 4250194 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2301. Min Act: -0.1700
Data Index: 2585679 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.2301. Min Act: -0.1700
Data Index: 900277 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5426. Min Range: -6.5426
Max Act: 6.1988. Min Act: -0.1700
Data Index: 3790956 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19