Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 415 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.5310. Min Act: -0.1700
Data Index: 7020070 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.5310. Min Act: -0.1699
Data Index: 262575 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4959. Min Act: -0.1698
Data Index: 7974256 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4783. Min Act: -0.1697
Data Index: 1026718 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4783. Min Act: -0.1700
Data Index: 7849721 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4431. Min Act: -0.1700
Data Index: 8206357 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4783. Min Act: -0.1697
Data Index: 4559668 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4431. Min Act: -0.1694
Data Index: 5589253 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1699
Data Index: 5158241 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4431. Min Act: -0.1699
Data Index: 2942397 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4431. Min Act: -0.1670
Data Index: 956641 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1699
Data Index: 3880989 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1700
Data Index: 5206984 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4431. Min Act: -0.1700
Data Index: 4285506 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1691
Data Index: 3772038 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4079. Min Act: -0.1699
Data Index: 4718906 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1700
Data Index: 15637 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1700
Data Index: 5172480 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4255. Min Act: -0.1667
Data Index: 2444452 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5310. Min Range: -1.5310
Max Act: 1.4079. Min Act: -0.1698
Data Index: 6638365 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19