Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1687 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5942. Min Range: -10.5942
Max Act: 10.5942. Min Act: -0.1700
Data Index: 3428200 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5942. Min Range: -10.5942
Max Act: 10.4067. Min Act: -0.1700
Data Index: 7635706 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5942. Min Range: -10.5942
Max Act: 10.4067. Min Act: -0.1700
Data Index: 3848310 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5942. Min Range: -10.5942
Max Act: 10.3442. Min Act: -0.1699
Data Index: 4074358 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.9692. Min Act: -0.1700
Data Index: 7294033 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.8442. Min Act: -0.1700
Data Index: 4705274 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.8442. Min Act: -0.1700
Data Index: 7294020 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.7817. Min Act: -0.1700
Data Index: 4358503 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.7192. Min Act: -0.1700
Data Index: 5683652 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.7817. Min Act: -0.1700
Data Index: 7277095 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.7192. Min Act: -0.1700
Data Index: 6673599 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.7192. Min Act: -0.1700
Data Index: 7155476 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.5942. Min Act: -0.1700
Data Index: 6887182 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.5317. Min Act: -0.1700
Data Index: 4944136 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.5942. Min Act: -0.1700
Data Index: 5789107 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.5317. Min Act: -0.1700
Data Index: 5063141 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.4692. Min Act: -0.1700
Data Index: 2337482 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.4692. Min Act: -0.1700
Data Index: 5457476 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.4692. Min Act: -0.1700
Data Index: 7750058 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5942. Min Range: -10.5942
Max Act: 9.4067. Min Act: -0.1700
Data Index: 1271073 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19