Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4579. Min Range: -6.4579
Max Act: 6.4579. Min Act: -0.1700
Data Index: 3774344 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4579. Min Range: -6.4579
Max Act: 6.3016. Min Act: -0.1700
Data Index: 7464406 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4579. Min Range: -6.4579
Max Act: 6.2391. Min Act: -0.1700
Data Index: 5891505 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4579. Min Range: -6.4579
Max Act: 6.1141. Min Act: -0.1700
Data Index: 5665368 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4579. Min Range: -6.4579
Max Act: 6.0829. Min Act: -0.1700
Data Index: 3871182 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.9579. Min Act: -0.1700
Data Index: 6124535 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.9579. Min Act: -0.1700
Data Index: 2623951 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6704545 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.9579. Min Act: -0.1700
Data Index: 1634662 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8641. Min Act: -0.1700
Data Index: 2467335 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8641. Min Act: -0.1700
Data Index: 8464358 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8329. Min Act: -0.1700
Data Index: 8143484 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8954. Min Act: -0.1700
Data Index: 4803922 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8954. Min Act: -0.1700
Data Index: 6131991 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8641. Min Act: -0.1700
Data Index: 6835814 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8329. Min Act: -0.1700
Data Index: 2364681 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8329. Min Act: -0.1700
Data Index: 3175319 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8016. Min Act: -0.1700
Data Index: 8305585 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8016. Min Act: -0.1700
Data Index: 4926603 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4579. Min Range: -6.4579
Max Act: 5.8016. Min Act: -0.1700
Data Index: 4902529 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19