Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 197 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.9482. Min Act: -0.1700
Data Index: 478520 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.7295. Min Act: -0.1700
Data Index: 8826612 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6670. Min Act: -0.1700
Data Index: 89584 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6357. Min Act: -0.1700
Data Index: 1805144 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6357. Min Act: -0.1700
Data Index: 7893701 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6357. Min Act: -0.1700
Data Index: 448553 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6357. Min Act: -0.1700
Data Index: 1216005 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6357. Min Act: -0.1700
Data Index: 3412674 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8230309 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6045. Min Act: -0.1700
Data Index: 6687490 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6045. Min Act: -0.1700
Data Index: 795445 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6045. Min Act: -0.1700
Data Index: 550724 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.6045. Min Act: -0.1700
Data Index: 1651236 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 6724423 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 8399962 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 5781155 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 8747454 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 8168425 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 7017165 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9482. Min Range: -5.9482
Max Act: 5.5732. Min Act: -0.1700
Data Index: 2495521 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19