Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 532 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1365. Min Range: -6.1365
Max Act: 6.1365. Min Act: -0.1700
Data Index: 7430608 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1365. Min Range: -6.1365
Max Act: 6.0428. Min Act: -0.1700
Data Index: 8546046 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1365. Min Range: -6.1365
Max Act: 6.0115. Min Act: -0.1700
Data Index: 6308468 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.9490. Min Act: -0.1700
Data Index: 4990051 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.9178. Min Act: -0.1700
Data Index: 2382899 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.8553. Min Act: -0.1700
Data Index: 1557963 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.7928. Min Act: -0.1700
Data Index: 5304926 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.7615. Min Act: -0.1700
Data Index: 2746478 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.7615. Min Act: -0.1700
Data Index: 3696738 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7977368 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6678. Min Act: -0.1700
Data Index: 4044806 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6990. Min Act: -0.1700
Data Index: 1306241 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6990. Min Act: -0.1700
Data Index: 7527223 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6990. Min Act: -0.1700
Data Index: 2086878 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6678. Min Act: -0.1700
Data Index: 6039696 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6120460 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2631064 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6429921 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.6053. Min Act: -0.1700
Data Index: 6003228 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1365. Min Range: -6.1365
Max Act: 5.5740. Min Act: -0.1700
Data Index: 8325184 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19