Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.4899. Min Act: -0.1700
Data Index: 1068964 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.3649. Min Act: -0.1700
Data Index: 5238792 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.3336. Min Act: -0.1700
Data Index: 94198 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.2711. Min Act: -0.1700
Data Index: 2890137 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.2086. Min Act: -0.1700
Data Index: 6006445 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.1461. Min Act: -0.1700
Data Index: 5973596 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.1149. Min Act: -0.1700
Data Index: 6880356 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.0836. Min Act: -0.1700
Data Index: 1809626 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.0836. Min Act: -0.1700
Data Index: 7684896 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.0524. Min Act: -0.1700
Data Index: 5757839 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.0211. Min Act: -0.1700
Data Index: 6439328 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.0211. Min Act: -0.1700
Data Index: 3309303 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9899. Min Act: -0.1700
Data Index: 729917 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9899. Min Act: -0.1700
Data Index: 672207 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9899. Min Act: -0.1700
Data Index: 4949710 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4899. Min Range: -6.4899
Max Act: 6.0211. Min Act: -0.1700
Data Index: 6520247 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9586. Min Act: -0.1700
Data Index: 3761052 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9899. Min Act: -0.1700
Data Index: 4660357 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9586. Min Act: -0.1700
Data Index: 2223014 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4899. Min Range: -6.4899
Max Act: 5.9586. Min Act: -0.1700
Data Index: 3530210 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19