Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.9485. Min Act: -0.1700
Data Index: 8603790 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.9485. Min Act: -0.1700
Data Index: 4617255 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.8859. Min Act: -0.1700
Data Index: 3563804 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.9016. Min Act: -0.1700
Data Index: 7091377 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.8859. Min Act: -0.1700
Data Index: 7993675 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.8234. Min Act: -0.1700
Data Index: 4505093 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7921. Min Act: -0.1700
Data Index: 116655 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7921. Min Act: -0.1700
Data Index: 3882998 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.8547. Min Act: -0.1700
Data Index: 7600960 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.8390. Min Act: -0.1700
Data Index: 6321523 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.8234. Min Act: -0.1700
Data Index: 7600963 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7765. Min Act: -0.1700
Data Index: 3657949 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7608. Min Act: -0.1700
Data Index: 5514878 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7608. Min Act: -0.1700
Data Index: 844370 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7452. Min Act: -0.1700
Data Index: 4903848 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7296. Min Act: -0.1700
Data Index: 5552116 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.7765. Min Act: -0.1700
Data Index: 3947452 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.6983. Min Act: -0.1700
Data Index: 3563805 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.6670. Min Act: -0.1700
Data Index: 8473847 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9485. Min Range: -3.9485
Max Act: 3.6670. Min Act: -0.1700
Data Index: 6701353 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19