Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.8112. Min Act: -0.1700
Data Index: 202579 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.6862. Min Act: -0.1700
Data Index: 3486902 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.6862. Min Act: -0.1700
Data Index: 4719272 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.5612. Min Act: -0.1700
Data Index: 3562936 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.5299. Min Act: -0.1700
Data Index: 8214439 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.5299. Min Act: -0.1700
Data Index: 7768446 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.4987. Min Act: -0.1700
Data Index: 5996152 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.4987. Min Act: -0.1700
Data Index: 3272073 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.4674. Min Act: -0.1700
Data Index: 4815752 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.4362. Min Act: -0.1700
Data Index: 169443 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.4362. Min Act: -0.1700
Data Index: 6824784 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.4049. Min Act: -0.1700
Data Index: 7766773 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.3424. Min Act: -0.1700
Data Index: 4096771 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.3112. Min Act: -0.1700
Data Index: 5336139 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.3112. Min Act: -0.1700
Data Index: 1397883 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.2799. Min Act: -0.1700
Data Index: 7702877 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.2174. Min Act: -0.1700
Data Index: 2440442 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.2174. Min Act: -0.1700
Data Index: 4127624 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.2174. Min Act: -0.1700
Data Index: 4555693 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8112. Min Range: -7.8112
Max Act: 7.2174. Min Act: -0.1700
Data Index: 4127625 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19