Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1238. Min Range: -9.1238
Max Act: 9.1238. Min Act: -0.1700
Data Index: 2586998 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1238. Min Range: -9.1238
Max Act: 8.3738. Min Act: -0.1700
Data Index: 3808813 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1238. Min Range: -9.1238
Max Act: 8.2488. Min Act: -0.1700
Data Index: 3611317 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1238. Min Range: -9.1238
Max Act: 8.2488. Min Act: -0.1700
Data Index: 2312815 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1238. Min Range: -9.1238
Max Act: 8.3113. Min Act: -0.1700
Data Index: 3977058 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1238. Min Range: -9.1238
Max Act: 8.1863. Min Act: -0.1700
Data Index: 8619781 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1238. Min Range: -9.1238
Max Act: 8.0613. Min Act: -0.1700
Data Index: 7832956 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.9363. Min Act: -0.1700
Data Index: 7778360 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.9988. Min Act: -0.1700
Data Index: 8037532 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.8738. Min Act: -0.1700
Data Index: 5682043 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.8738. Min Act: -0.1700
Data Index: 5948659 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.7488. Min Act: -0.1700
Data Index: 3415487 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.8113. Min Act: -0.1700
Data Index: 3507228 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.8113. Min Act: -0.1700
Data Index: 2598964 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.8738. Min Act: -0.1700
Data Index: 2161273 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.8113. Min Act: -0.1700
Data Index: 3210746 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.6863. Min Act: -0.1700
Data Index: 6100914 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.7488. Min Act: -0.1700
Data Index: 8199502 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.7488. Min Act: -0.1700
Data Index: 5186061 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1238. Min Range: -9.1238
Max Act: 7.7176. Min Act: -0.1700
Data Index: 4897147 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19