Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1567. Min Range: -8.1567
Max Act: 8.1567. Min Act: -0.1700
Data Index: 7211877 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.5629. Min Act: -0.1700
Data Index: 3895461 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.3754. Min Act: -0.1700
Data Index: 4810263 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.3754. Min Act: -0.1700
Data Index: 3585516 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.2504. Min Act: -0.1700
Data Index: 3895467 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.2192. Min Act: -0.1700
Data Index: 3895468 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.2504. Min Act: -0.1700
Data Index: 3895489 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.1254. Min Act: -0.1700
Data Index: 5180695 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.1254. Min Act: -0.1700
Data Index: 3895482 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0942. Min Act: -0.1700
Data Index: 4402346 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0629. Min Act: -0.1700
Data Index: 4460254 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0317. Min Act: -0.1700
Data Index: 2604280 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0317. Min Act: -0.1700
Data Index: 3134390 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0004. Min Act: -0.1700
Data Index: 597966 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0004. Min Act: -0.1700
Data Index: 8507222 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0004. Min Act: -0.1700
Data Index: 5180704 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.0004. Min Act: -0.1700
Data Index: 6020248 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1567. Min Range: -8.1567
Max Act: 6.9379. Min Act: -0.1700
Data Index: 3895454 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1567. Min Range: -8.1567
Max Act: 6.9067. Min Act: -0.1700
Data Index: 1261222 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1567. Min Range: -8.1567
Max Act: 6.9692. Min Act: -0.1700
Data Index: 7958985 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19