Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0395. Min Range: -6.0395
Max Act: 6.0395. Min Act: -0.1700
Data Index: 2771245 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.7895. Min Act: -0.1700
Data Index: 5984846 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.7582. Min Act: -0.1700
Data Index: 148544 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.6645. Min Act: -0.1700
Data Index: 8819598 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.6957. Min Act: -0.1700
Data Index: 5391154 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.6957. Min Act: -0.1700
Data Index: 705618 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.5707. Min Act: -0.1700
Data Index: 4250323 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.5707. Min Act: -0.1700
Data Index: 5030306 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4770. Min Act: -0.1700
Data Index: 1969371 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.5082. Min Act: -0.1700
Data Index: 984333 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4770. Min Act: -0.1700
Data Index: 4154041 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4770. Min Act: -0.1700
Data Index: 7116718 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4457. Min Act: -0.1700
Data Index: 6512810 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4457. Min Act: -0.1700
Data Index: 7428534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4145. Min Act: -0.1700
Data Index: 5185692 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4145. Min Act: -0.1700
Data Index: 5027912 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4145. Min Act: -0.1700
Data Index: 8620703 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4145. Min Act: -0.1700
Data Index: 7759668 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4457. Min Act: -0.1700
Data Index: 5926477 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0395. Min Range: -6.0395
Max Act: 5.4145. Min Act: -0.1700
Data Index: 5495601 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19