Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.6209. Min Act: -0.1700
Data Index: 2716556 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.5272. Min Act: -0.1700
Data Index: 7995578 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.4022. Min Act: -0.1700
Data Index: 2648407 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.3709. Min Act: -0.1700
Data Index: 5366450 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.4334. Min Act: -0.1700
Data Index: 3187264 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.3397. Min Act: -0.1700
Data Index: 8443042 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.3084. Min Act: -0.1700
Data Index: 2166023 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.2459. Min Act: -0.1700
Data Index: 3807277 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.2772. Min Act: -0.1700
Data Index: 3989692 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.2147. Min Act: -0.1700
Data Index: 240916 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.2147. Min Act: -0.1700
Data Index: 2376287 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.2459. Min Act: -0.1700
Data Index: 7797970 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.2459. Min Act: -0.1700
Data Index: 6403846 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1834. Min Act: -0.1700
Data Index: 7999992 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1834. Min Act: -0.1700
Data Index: 592056 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1834. Min Act: -0.1700
Data Index: 994201 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1522. Min Act: -0.1700
Data Index: 457003 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1522. Min Act: -0.1700
Data Index: 2029507 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1834. Min Act: -0.1700
Data Index: 442497 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6209. Min Range: -6.6209
Max Act: 6.1209. Min Act: -0.1700
Data Index: 135701 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19