Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 678 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.4367. Min Act: -0.1700
Data Index: 5956465 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.3742. Min Act: -0.1700
Data Index: 8228502 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.2492. Min Act: -0.1700
Data Index: 5802139 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.2492. Min Act: -0.1700
Data Index: 8107377 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.2805. Min Act: -0.1700
Data Index: 1146294 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.1242. Min Act: -0.1700
Data Index: 4796714 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.0617. Min Act: -0.1700
Data Index: 8774745 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.0930. Min Act: -0.1700
Data Index: 2207133 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9992. Min Act: -0.1700
Data Index: 2378712 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.0305. Min Act: -0.1700
Data Index: 5575714 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9992. Min Act: -0.1700
Data Index: 7058031 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9992. Min Act: -0.1700
Data Index: 2974700 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4367. Min Range: -5.4367
Max Act: 5.0305. Min Act: -0.1700
Data Index: 5574837 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9680. Min Act: -0.1700
Data Index: 2382548 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9992. Min Act: -0.1699
Data Index: 8371020 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9367. Min Act: -0.1700
Data Index: 6481850 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9680. Min Act: -0.1700
Data Index: 121896 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9680. Min Act: -0.1700
Data Index: 2410501 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9680. Min Act: -0.1700
Data Index: 492289 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4367. Min Range: -5.4367
Max Act: 4.9367. Min Act: -0.1700
Data Index: 257110 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19