Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.4205. Min Act: -0.1700
Data Index: 570290 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.3580. Min Act: -0.1700
Data Index: 8822933 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1705. Min Act: -0.1700
Data Index: 7550387 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1393. Min Act: -0.1700
Data Index: 5625671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1080. Min Act: -0.1700
Data Index: 5757594 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.1393. Min Act: -0.1700
Data Index: 1623314 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.0768. Min Act: -0.1700
Data Index: 570289 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.0455. Min Act: -0.1700
Data Index: 320460 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4205. Min Range: -5.4205
Max Act: 5.0143. Min Act: -0.1700
Data Index: 547073 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.9518. Min Act: -0.1700
Data Index: 1763361 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.8893. Min Act: -0.1700
Data Index: 4793410 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.8580. Min Act: -0.1700
Data Index: 4372057 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.8580. Min Act: -0.1700
Data Index: 6809635 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.8580. Min Act: -0.1700
Data Index: 6336215 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.8268. Min Act: -0.1700
Data Index: 3792724 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.7955. Min Act: -0.1700
Data Index: 8412463 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.7330. Min Act: -0.1700
Data Index: 587755 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.7330. Min Act: -0.1700
Data Index: 5249412 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.7018. Min Act: -0.1700
Data Index: 3578034 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4205. Min Range: -5.4205
Max Act: 4.7330. Min Act: -0.1700
Data Index: 6582645 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19