Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0347. Min Range: -4.0347
Max Act: 4.0347. Min Act: -0.1700
Data Index: 6613405 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.9409. Min Act: -0.1700
Data Index: 5980722 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.9409. Min Act: -0.1700
Data Index: 6727522 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.9409. Min Act: -0.1700
Data Index: 3253337 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.9097. Min Act: -0.1700
Data Index: 5994172 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.8315. Min Act: -0.1700
Data Index: 6089653 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.8159. Min Act: -0.1700
Data Index: 2553236 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.8315. Min Act: -0.1700
Data Index: 4930919 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.8159. Min Act: -0.1700
Data Index: 1012345 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.8002. Min Act: -0.1700
Data Index: 6727528 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.8002. Min Act: -0.1700
Data Index: 3623634 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7846. Min Act: -0.1700
Data Index: 8439213 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7689. Min Act: -0.1700
Data Index: 2197158 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7533. Min Act: -0.1700
Data Index: 4438799 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7533. Min Act: -0.1700
Data Index: 2747322 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7689. Min Act: -0.1700
Data Index: 1280526 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7064. Min Act: -0.1700
Data Index: 330397 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7220. Min Act: -0.1700
Data Index: 2898321 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7220. Min Act: -0.1700
Data Index: 2680772 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0347. Min Range: -4.0347
Max Act: 3.7220. Min Act: -0.1700
Data Index: 967322 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19