Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2282 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.4519. Min Act: -0.1700
Data Index: 2963317 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.3376. Min Act: -0.1700
Data Index: 3981243 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.3212. Min Act: -0.1700
Data Index: 995516 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.3376. Min Act: -0.1700
Data Index: 7645341 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.3048. Min Act: -0.1700
Data Index: 6844139 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.3048. Min Act: -0.1700
Data Index: 6888551 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2719. Min Act: -0.1700
Data Index: 4521623 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2719. Min Act: -0.1700
Data Index: 5341035 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2554. Min Act: -0.1700
Data Index: 2189487 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2388. Min Act: -0.1700
Data Index: 4722868 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2223. Min Act: -0.1700
Data Index: 6624253 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2388. Min Act: -0.1700
Data Index: 83828 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2388. Min Act: -0.1700
Data Index: 362423 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2223. Min Act: -0.1700
Data Index: 7380775 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2223. Min Act: -0.1700
Data Index: 4849992 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2057. Min Act: -0.1700
Data Index: 8270545 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2057. Min Act: -0.1700
Data Index: 5290252 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2057. Min Act: -0.1700
Data Index: 7699499 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2057. Min Act: -0.1700
Data Index: 3981244 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4519. Min Range: -2.4519
Max Act: 2.2057. Min Act: -0.1700
Data Index: 5597554 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19