Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4626 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.4018. Min Range: -13.4018
Max Act: 13.4018. Min Act: -0.1700
Data Index: 1979380 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.4018. Min Range: -13.4018
Max Act: 13.2768. Min Act: -0.1700
Data Index: 2605340 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.4018. Min Range: -13.4018
Max Act: 13.2143. Min Act: -0.1700
Data Index: 3839205 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.4018. Min Range: -13.4018
Max Act: 13.0268. Min Act: -0.1700
Data Index: 7636179 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.4018. Min Range: -13.4018
Max Act: 13.0893. Min Act: -0.1700
Data Index: 8788597 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.4018. Min Range: -13.4018
Max Act: 13.0268. Min Act: -0.1700
Data Index: 6970815 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.9643. Min Act: -0.1700
Data Index: 188513 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.9643. Min Act: -0.1700
Data Index: 7630160 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.9643. Min Act: -0.1700
Data Index: 8085556 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.8393. Min Act: -0.1699
Data Index: 6893490 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.8393. Min Act: -0.1700
Data Index: 3799091 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.8393. Min Act: -0.1700
Data Index: 845151 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.8393. Min Act: -0.1700
Data Index: 4640658 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.8393. Min Act: -0.1700
Data Index: 4889579 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.8393. Min Act: -0.1700
Data Index: 3973869 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.7768. Min Act: -0.1700
Data Index: 8547429 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.7768. Min Act: -0.1700
Data Index: 531229 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.7768. Min Act: -0.1700
Data Index: 5179278 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.7143. Min Act: -0.1700
Data Index: 5111598 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.4018. Min Range: -13.4018
Max Act: 12.7143. Min Act: -0.1700
Data Index: 5426606 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19