Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.5199. Min Act: -0.1700
Data Index: 2570059 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.3012. Min Act: -0.1700
Data Index: 5748175 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.1762. Min Act: -0.1700
Data Index: 8267487 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.1449. Min Act: -0.1700
Data Index: 2999560 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.1137. Min Act: -0.1700
Data Index: 6291685 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.0512. Min Act: -0.1700
Data Index: 6978528 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.0199. Min Act: -0.1698
Data Index: 6238075 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5199. Min Range: -5.5199
Max Act: 5.0199. Min Act: -0.1700
Data Index: 8507916 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.9262. Min Act: -0.1699
Data Index: 2207173 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.9262. Min Act: -0.1688
Data Index: 8284720 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8949. Min Act: -0.1700
Data Index: 1271236 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.9262. Min Act: -0.1700
Data Index: 2451196 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8949. Min Act: -0.1700
Data Index: 1767978 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8949. Min Act: -0.1700
Data Index: 6878356 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8637. Min Act: -0.1700
Data Index: 750290 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8637. Min Act: -0.1700
Data Index: 183834 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8637. Min Act: -0.1690
Data Index: 626745 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8324. Min Act: -0.1700
Data Index: 2349571 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8637. Min Act: -0.1700
Data Index: 7655894 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5199. Min Range: -5.5199
Max Act: 4.8324. Min Act: -0.1700
Data Index: 704333 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19