Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.7383. Min Act: -0.1700
Data Index: 5858503 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.6758. Min Act: -0.1700
Data Index: 2577112 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.4883. Min Act: -0.1700
Data Index: 3220021 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.4883. Min Act: -0.1700
Data Index: 7455525 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.5195. Min Act: -0.1700
Data Index: 4891761 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.4258. Min Act: -0.1700
Data Index: 4594091 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3945. Min Act: -0.1700
Data Index: 6646129 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3320. Min Act: -0.1700
Data Index: 7482430 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3320. Min Act: -0.1700
Data Index: 329064 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.3320. Min Act: -0.1700
Data Index: 2768407 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2695. Min Act: -0.1700
Data Index: 7619927 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2695. Min Act: -0.1700
Data Index: 6147655 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2382. Min Act: -0.1700
Data Index: 7065395 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2382. Min Act: -0.1700
Data Index: 7101399 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2382. Min Act: -0.1700
Data Index: 2537664 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2070. Min Act: -0.1700
Data Index: 2856282 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2070. Min Act: -0.1700
Data Index: 807589 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1757. Min Act: -0.1700
Data Index: 7270822 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.2070. Min Act: -0.1700
Data Index: 2916026 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7383. Min Range: -4.7383
Max Act: 4.1757. Min Act: -0.1700
Data Index: 1646431 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19