Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2429 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1581739 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.6507. Min Act: -0.1700
Data Index: 7309005 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.6194. Min Act: -0.1700
Data Index: 5925019 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.5882. Min Act: -0.1700
Data Index: 1596748 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.5882. Min Act: -0.1700
Data Index: 818640 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.5257. Min Act: -0.1700
Data Index: 5631852 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4944. Min Act: -0.1700
Data Index: 1238972 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4632. Min Act: -0.1700
Data Index: 97611 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4882989 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4632. Min Act: -0.1700
Data Index: 1029529 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3962547 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4632. Min Act: -0.1700
Data Index: 632730 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 8717664 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4007. Min Act: -0.1700
Data Index: 3484636 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3874945 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 5354471 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 8002090 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3382. Min Act: -0.1700
Data Index: 7120672 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 5690914 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4007. Min Act: -0.1700
Data Index: 3376552 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19