Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2026 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.4459. Min Act: -0.1700
Data Index: 5880580 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.3522. Min Act: -0.1700
Data Index: 3157222 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.2272. Min Act: -0.1700
Data Index: 5447141 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.1959. Min Act: -0.1700
Data Index: 1296989 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.2272. Min Act: -0.1700
Data Index: 5059248 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.1647. Min Act: -0.1700
Data Index: 4148952 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.1959. Min Act: -0.1700
Data Index: 8242045 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.0397. Min Act: -0.1700
Data Index: 8452708 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4459. Min Range: -7.4459
Max Act: 7.0084. Min Act: -0.1700
Data Index: 5660303 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.8209. Min Act: -0.1700
Data Index: 4625519 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.8522. Min Act: -0.1700
Data Index: 7303885 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.7897. Min Act: -0.1700
Data Index: 7900122 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.7584. Min Act: -0.1700
Data Index: 3382755 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.7272. Min Act: -0.1700
Data Index: 2180878 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.7272. Min Act: -0.1700
Data Index: 1418341 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.6334. Min Act: -0.1700
Data Index: 8152443 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.6022. Min Act: -0.1700
Data Index: 5131262 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.6334. Min Act: -0.1700
Data Index: 4158040 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.5397. Min Act: -0.1700
Data Index: 393940 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4459. Min Range: -7.4459
Max Act: 6.5709. Min Act: -0.1700
Data Index: 7362325 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19