Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1111 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2022. Min Range: -7.2022
Max Act: 7.2022. Min Act: -0.1700
Data Index: 5315787 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2022. Min Range: -7.2022
Max Act: 7.0147. Min Act: -0.1700
Data Index: 221132 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.9522. Min Act: -0.1700
Data Index: 3389727 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.9522. Min Act: -0.1700
Data Index: 4549534 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.9210. Min Act: -0.1700
Data Index: 4871716 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.8272. Min Act: -0.1700
Data Index: 2518107 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.8585. Min Act: -0.1700
Data Index: 6194993 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7404699 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.7960. Min Act: -0.1700
Data Index: 2554365 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.7960. Min Act: -0.1700
Data Index: 6104843 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.7335. Min Act: -0.1700
Data Index: 8166747 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.7022. Min Act: -0.1700
Data Index: 317000 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6397. Min Act: -0.1700
Data Index: 5546572 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6710. Min Act: -0.1700
Data Index: 3652888 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6710. Min Act: -0.1700
Data Index: 2337563 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6397. Min Act: -0.1700
Data Index: 3075760 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6397. Min Act: -0.1700
Data Index: 8367451 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6397. Min Act: -0.1700
Data Index: 8037697 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6085. Min Act: -0.1700
Data Index: 6286525 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2022. Min Range: -7.2022
Max Act: 6.6085. Min Act: -0.1700
Data Index: 2105037 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19