Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.2466. Min Act: -0.1700
Data Index: 6445552 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.2153. Min Act: -0.1700
Data Index: 857911 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.1841. Min Act: -0.1700
Data Index: 2704904 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.1841. Min Act: -0.1700
Data Index: 4811116 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.1216. Min Act: -0.1700
Data Index: 7250330 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0903. Min Act: -0.1700
Data Index: 1846259 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0591. Min Act: -0.1700
Data Index: 1372364 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0591. Min Act: -0.1700
Data Index: 7978460 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0278. Min Act: -0.1700
Data Index: 8119777 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0278. Min Act: -0.1700
Data Index: 2844068 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9966. Min Act: -0.1700
Data Index: 7611342 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0278. Min Act: -0.1700
Data Index: 1227110 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0278. Min Act: -0.1700
Data Index: 2543396 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9966. Min Act: -0.1700
Data Index: 384951 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2466. Min Range: -6.2466
Max Act: 6.0278. Min Act: -0.1700
Data Index: 1435945 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9966. Min Act: -0.1700
Data Index: 2585145 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9966. Min Act: -0.1700
Data Index: 1949580 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9653. Min Act: -0.1700
Data Index: 3435501 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9653. Min Act: -0.1700
Data Index: 6536522 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2466. Min Range: -6.2466
Max Act: 5.9653. Min Act: -0.1700
Data Index: 6929143 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19