Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.7493. Min Act: -0.1700
Data Index: 2904638 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.6868. Min Act: -0.1700
Data Index: 2714883 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.6243. Min Act: -0.1700
Data Index: 1480699 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.6243. Min Act: -0.1700
Data Index: 4692350 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.5618. Min Act: -0.1700
Data Index: 4304364 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.4993. Min Act: -0.1700
Data Index: 3595870 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.4368. Min Act: -0.1700
Data Index: 675435 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.2493. Min Act: -0.1700
Data Index: 568267 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.3118. Min Act: -0.1700
Data Index: 3108926 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.2493. Min Act: -0.1700
Data Index: 4764031 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.2493. Min Act: -0.1700
Data Index: 1683641 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1868. Min Act: -0.1700
Data Index: 3455136 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1868. Min Act: -0.1700
Data Index: 6248236 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1868. Min Act: -0.1700
Data Index: 8557188 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1868. Min Act: -0.1700
Data Index: 4841546 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1868. Min Act: -0.1700
Data Index: 6735504 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1868. Min Act: -0.1700
Data Index: 1007480 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.2493. Min Act: -0.1700
Data Index: 2199264 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.1243. Min Act: -0.1700
Data Index: 5773580 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7493. Min Range: -8.7493
Max Act: 8.0618. Min Act: -0.1700
Data Index: 4657576 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19