Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.7541. Min Act: -0.1700
Data Index: 6818776 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.6603. Min Act: -0.1700
Data Index: 5069365 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.6291. Min Act: -0.1700
Data Index: 3358664 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.5666. Min Act: -0.1700
Data Index: 2008225 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.5666. Min Act: -0.1700
Data Index: 3952980 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.5041. Min Act: -0.1700
Data Index: 4048060 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.4728. Min Act: -0.1700
Data Index: 2726203 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.5041. Min Act: -0.1700
Data Index: 6731074 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.5041. Min Act: -0.1700
Data Index: 2315967 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.4728. Min Act: -0.1700
Data Index: 8433314 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.5041. Min Act: -0.1700
Data Index: 6253019 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.4728. Min Act: -0.1700
Data Index: 6971829 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.4103. Min Act: -0.1700
Data Index: 7608025 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.4103. Min Act: -0.1700
Data Index: 623041 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.4103. Min Act: -0.1700
Data Index: 4618302 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.3791. Min Act: -0.1700
Data Index: 4316699 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.3478. Min Act: -0.1700
Data Index: 4622209 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.3478. Min Act: -0.1700
Data Index: 7160273 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.3478. Min Act: -0.1700
Data Index: 3462300 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7541. Min Range: -7.7541
Max Act: 7.3478. Min Act: -0.1700
Data Index: 6213650 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19