Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1222. Min Range: -8.1222
Max Act: 8.1222. Min Act: -0.1700
Data Index: 5030315 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.9347. Min Act: -0.1700
Data Index: 8078389 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.6534. Min Act: -0.1700
Data Index: 2538049 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.6222. Min Act: -0.1700
Data Index: 4051309 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.5284. Min Act: -0.1700
Data Index: 4959156 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.4972. Min Act: -0.1700
Data Index: 594657 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.4972. Min Act: -0.1700
Data Index: 6183683 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.4972. Min Act: -0.1700
Data Index: 1696345 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.4659. Min Act: -0.1700
Data Index: 1663393 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.3409. Min Act: -0.1700
Data Index: 8465083 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.3097. Min Act: -0.1700
Data Index: 6061638 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.3409. Min Act: -0.1700
Data Index: 2710604 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2784. Min Act: -0.1700
Data Index: 1680634 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.3097. Min Act: -0.1700
Data Index: 3178231 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2784. Min Act: -0.1700
Data Index: 7724202 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2784. Min Act: -0.1700
Data Index: 1449689 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2784. Min Act: -0.1700
Data Index: 1504875 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2472. Min Act: -0.1700
Data Index: 5632981 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2159. Min Act: -0.1700
Data Index: 6915880 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1222. Min Range: -8.1222
Max Act: 7.2784. Min Act: -0.1700
Data Index: 4293493 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19