Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 829 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3207. Min Range: -8.3207
Max Act: 8.3207. Min Act: -0.1700
Data Index: 5075243 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3207. Min Range: -8.3207
Max Act: 8.2582. Min Act: -0.1700
Data Index: 3228135 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3207. Min Range: -8.3207
Max Act: 8.1332. Min Act: -0.1700
Data Index: 6365206 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3207. Min Range: -8.3207
Max Act: 8.0394. Min Act: -0.1700
Data Index: 2066222 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.6957. Min Act: -0.1700
Data Index: 4430472 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.6644. Min Act: -0.1700
Data Index: 5286150 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.6332. Min Act: -0.1700
Data Index: 1122978 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.6332. Min Act: -0.1700
Data Index: 8513479 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.6332. Min Act: -0.1700
Data Index: 1405106 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.5082. Min Act: -0.1700
Data Index: 2271294 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.4144. Min Act: -0.1700
Data Index: 2138093 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.4457. Min Act: -0.1700
Data Index: 2050999 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.4144. Min Act: -0.1700
Data Index: 4737674 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.3832. Min Act: -0.1700
Data Index: 4032103 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.3207. Min Act: -0.1700
Data Index: 1982060 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.3832. Min Act: -0.1700
Data Index: 4879430 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.3207. Min Act: -0.1700
Data Index: 1300127 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.3207. Min Act: -0.1700
Data Index: 3942691 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.3519. Min Act: -0.1700
Data Index: 4844008 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3207. Min Range: -8.3207
Max Act: 7.2894. Min Act: -0.1700
Data Index: 4701674 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19