Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.7622. Min Act: -0.1700
Data Index: 5536319 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.6685. Min Act: -0.1700
Data Index: 4784508 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.5747. Min Act: -0.1700
Data Index: 8184436 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.6060. Min Act: -0.1700
Data Index: 6740540 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.5435. Min Act: -0.1700
Data Index: 3827834 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.5122. Min Act: -0.1700
Data Index: 4606096 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.4497. Min Act: -0.1700
Data Index: 8231345 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.3560. Min Act: -0.1700
Data Index: 7979000 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.3560. Min Act: -0.1700
Data Index: 4534686 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.2935. Min Act: -0.1700
Data Index: 4834845 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.2622. Min Act: -0.1700
Data Index: 4641612 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.1997. Min Act: -0.1700
Data Index: 7106726 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.1372. Min Act: -0.1700
Data Index: 3827217 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.1060. Min Act: -0.1700
Data Index: 6553038 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.1060. Min Act: -0.1700
Data Index: 226876 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.1372. Min Act: -0.1700
Data Index: 2807276 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.0747. Min Act: -0.1700
Data Index: 226870 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.0747. Min Act: -0.1700
Data Index: 6515892 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.0747. Min Act: -0.1700
Data Index: 1411034 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7622. Min Range: -7.7622
Max Act: 7.0435. Min Act: -0.1700
Data Index: 5078932 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19