Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.8113. Min Act: -0.1700
Data Index: 2548191 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.7488. Min Act: -0.1700
Data Index: 7908378 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.7488. Min Act: -0.1700
Data Index: 1859687 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 1689610 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 7978053 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.6863. Min Act: -0.1700
Data Index: 6517632 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.6238. Min Act: -0.1700
Data Index: 4633674 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.5613. Min Act: -0.1700
Data Index: 2981557 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.5613. Min Act: -0.1700
Data Index: 5067993 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.5613. Min Act: -0.1700
Data Index: 2891742 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.5613. Min Act: -0.1700
Data Index: 76979 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4363. Min Act: -0.1700
Data Index: 7632311 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 6939128 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 6938584 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 26236 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 6910515 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 4864785 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 872054 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4363. Min Act: -0.1700
Data Index: 3312036 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8113. Min Range: -7.8113
Max Act: 7.4988. Min Act: -0.1700
Data Index: 6154936 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19