Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6360 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.6425. Min Act: -0.1700
Data Index: 2386557 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.6425. Min Act: -0.1700
Data Index: 6446258 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.5488. Min Act: -0.1699
Data Index: 890337 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.5175. Min Act: -0.1700
Data Index: 3766180 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 1694624 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 1303558 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 5922907 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 6207473 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.4550. Min Act: -0.1700
Data Index: 3766177 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.4238. Min Act: -0.1700
Data Index: 890340 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3925. Min Act: -0.1700
Data Index: 2069287 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3925. Min Act: -0.1700
Data Index: 4340555 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3613. Min Act: -0.1700
Data Index: 5446523 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3613. Min Act: -0.1698
Data Index: 890339 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3300. Min Act: -0.1700
Data Index: 4570189 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3300. Min Act: -0.1700
Data Index: 2295338 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3613. Min Act: -0.1700
Data Index: 6225712 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3300. Min Act: -0.1700
Data Index: 8740203 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.3300. Min Act: -0.1700
Data Index: 6446256 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6425. Min Range: -6.6425
Max Act: 6.2988. Min Act: -0.1700
Data Index: 1141770 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19