Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 492 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.3280. Min Act: -0.1700
Data Index: 4255101 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.2655. Min Act: -0.1700
Data Index: 5189403 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.2342. Min Act: -0.1700
Data Index: 171422 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.2030. Min Act: -0.1700
Data Index: 7425984 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.2030. Min Act: -0.1700
Data Index: 5035892 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.2030. Min Act: -0.1700
Data Index: 5944857 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.1717. Min Act: -0.1700
Data Index: 4522494 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.1092. Min Act: -0.1700
Data Index: 3274565 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2670060 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.0467. Min Act: -0.1700
Data Index: 120278 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.0467. Min Act: -0.1700
Data Index: 3295076 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.0467. Min Act: -0.1700
Data Index: 7789641 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3280. Min Range: -5.3280
Max Act: 5.0467. Min Act: -0.1700
Data Index: 1995943 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9842. Min Act: -0.1700
Data Index: 2236977 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9842. Min Act: -0.1700
Data Index: 7501371 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9530. Min Act: -0.1700
Data Index: 5194833 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9530. Min Act: -0.1700
Data Index: 5912544 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9530. Min Act: -0.1700
Data Index: 3242774 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9217. Min Act: -0.1700
Data Index: 6295245 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3280. Min Range: -5.3280
Max Act: 4.9530. Min Act: -0.1700
Data Index: 5919624 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19