Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.6147. Min Act: -0.1700
Data Index: 250942 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.6147. Min Act: -0.1700
Data Index: 1588954 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.6147. Min Act: -0.1700
Data Index: 3683361 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.5522. Min Act: -0.1700
Data Index: 8267931 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.4585. Min Act: -0.1700
Data Index: 8348418 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.4585. Min Act: -0.1700
Data Index: 4685902 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3960. Min Act: -0.1700
Data Index: 817197 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3960. Min Act: -0.1700
Data Index: 6907519 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3960. Min Act: -0.1700
Data Index: 478692 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3647. Min Act: -0.1700
Data Index: 7858442 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3960. Min Act: -0.1700
Data Index: 2509328 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3022. Min Act: -0.1700
Data Index: 6789994 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.3022. Min Act: -0.1700
Data Index: 5928028 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.2710. Min Act: -0.1700
Data Index: 4307214 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.2397. Min Act: -0.1700
Data Index: 2223578 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.2397. Min Act: -0.1700
Data Index: 8661586 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.2397. Min Act: -0.1700
Data Index: 1781482 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.2397. Min Act: -0.1700
Data Index: 3108882 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.2397. Min Act: -0.1700
Data Index: 819218 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6147. Min Range: -7.6147
Max Act: 7.1772. Min Act: -0.1700
Data Index: 2434017 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19