Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1157. Min Range: -5.1157
Max Act: 5.1157. Min Act: -0.1700
Data Index: 7869699 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1157. Min Range: -5.1157
Max Act: 5.0844. Min Act: -0.1700
Data Index: 3414874 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1157. Min Range: -5.1157
Max Act: 5.0532. Min Act: -0.1700
Data Index: 2228678 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1157. Min Range: -5.1157
Max Act: 5.0219. Min Act: -0.1700
Data Index: 13922 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.9594. Min Act: -0.1700
Data Index: 6796917 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.9594. Min Act: -0.1700
Data Index: 3255527 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.9594. Min Act: -0.1700
Data Index: 1311965 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.9594. Min Act: -0.1700
Data Index: 4187520 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.9594. Min Act: -0.1700
Data Index: 8771618 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.8969. Min Act: -0.1700
Data Index: 29912 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.8344. Min Act: -0.1700
Data Index: 4897235 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.8344. Min Act: -0.1700
Data Index: 4818844 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.8032. Min Act: -0.1700
Data Index: 8813601 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.8032. Min Act: -0.1700
Data Index: 3563083 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.7719. Min Act: -0.1700
Data Index: 1037783 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.7407. Min Act: -0.1700
Data Index: 768056 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.7407. Min Act: -0.1700
Data Index: 6790471 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.7407. Min Act: -0.1700
Data Index: 8666530 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.7407. Min Act: -0.1700
Data Index: 5841845 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1157. Min Range: -5.1157
Max Act: 4.7407. Min Act: -0.1700
Data Index: 904967 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19