Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.7076. Min Act: -0.1700
Data Index: 537663 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.5201. Min Act: -0.1700
Data Index: 5100606 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.3951. Min Act: -0.1700
Data Index: 3101316 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.2076. Min Act: -0.1700
Data Index: 3174341 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.2076. Min Act: -0.1700
Data Index: 3296495 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.1451. Min Act: -0.1700
Data Index: 4569824 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.0826. Min Act: -0.1700
Data Index: 2252299 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7076. Min Range: -8.7076
Max Act: 8.0513. Min Act: -0.1700
Data Index: 1493742 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.9888. Min Act: -0.1700
Data Index: 3808575 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.9576. Min Act: -0.1700
Data Index: 3101306 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.9576. Min Act: -0.1700
Data Index: 2900050 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8951. Min Act: -0.1700
Data Index: 7939320 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.9263. Min Act: -0.1700
Data Index: 3372845 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8951. Min Act: -0.1700
Data Index: 7509456 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8951. Min Act: -0.1700
Data Index: 6030028 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8638. Min Act: -0.1700
Data Index: 8816229 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8638. Min Act: -0.1700
Data Index: 197142 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8638. Min Act: -0.1700
Data Index: 5727475 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8326. Min Act: -0.1700
Data Index: 4000104 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7076. Min Range: -8.7076
Max Act: 7.8326. Min Act: -0.1700
Data Index: 2212612 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19