Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0472. Min Range: -8.0472
Max Act: 8.0472. Min Act: -0.1700
Data Index: 1819740 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.7347. Min Act: -0.1700
Data Index: 5157767 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.7034. Min Act: -0.1700
Data Index: 3971994 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.7034. Min Act: -0.1700
Data Index: 2228204 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.7347. Min Act: -0.1700
Data Index: 3587170 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.6722. Min Act: -0.1700
Data Index: 8259989 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.6409. Min Act: -0.1700
Data Index: 4259793 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.6097. Min Act: -0.1700
Data Index: 8173849 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.5784. Min Act: -0.1700
Data Index: 6542458 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.5784. Min Act: -0.1700
Data Index: 106096 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.5784. Min Act: -0.1700
Data Index: 3212782 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.5472. Min Act: -0.1700
Data Index: 6542461 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.5159. Min Act: -0.1700
Data Index: 2993891 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.5159. Min Act: -0.1700
Data Index: 3152446 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.4847. Min Act: -0.1700
Data Index: 8130027 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.4847. Min Act: -0.1700
Data Index: 7437664 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.4534. Min Act: -0.1700
Data Index: 1817650 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.4534. Min Act: -0.1700
Data Index: 4207924 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.4534. Min Act: -0.1700
Data Index: 1993162 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0472. Min Range: -8.0472
Max Act: 7.4534. Min Act: -0.1700
Data Index: 6241899 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19