Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3385 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8971. Min Act: -0.1700
Data Index: 3077730 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8812. Min Act: -0.1700
Data Index: 465962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8812. Min Act: -0.1700
Data Index: 4536287 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8653. Min Act: -0.1700
Data Index: 5170519 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8812. Min Act: -0.1700
Data Index: 3962987 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8812. Min Act: -0.1700
Data Index: 3731621 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8812. Min Act: -0.1700
Data Index: 4957755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8812. Min Act: -0.1700
Data Index: 990402 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8653. Min Act: -0.1700
Data Index: 2175430 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8653. Min Act: -0.1700
Data Index: 5170518 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8653. Min Act: -0.1700
Data Index: 4745673 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 3651598 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8335. Min Act: -0.1700
Data Index: 3736924 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 4809085 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 6994938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 4282067 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 7049003 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 8454071 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8494. Min Act: -0.1700
Data Index: 8555360 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8971. Min Range: -2.8971
Max Act: 2.8335. Min Act: -0.1700
Data Index: 1158574 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19