Model: None
Dataset: The Pile
Neuron 2623 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.6442. Min Act: -0.1700
Data Index: 5555337 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.6129. Min Act: -0.1700
Data Index: 3104219 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5816. Min Act: -0.1700
Data Index: 6231568 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5816. Min Act: -0.1700
Data Index: 2906891 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5659. Min Act: -0.1700
Data Index: 10201593 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5659. Min Act: -0.1700
Data Index: 8914804 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5346. Min Act: -0.1700
Data Index: 2149533 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5346. Min Act: -0.1700
Data Index: 2119691 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5346. Min Act: -0.1700
Data Index: 6509159 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5346. Min Act: -0.1700
Data Index: 148728 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5346. Min Act: -0.1700
Data Index: 4939566 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5189. Min Act: -0.1700
Data Index: 7753181 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5189. Min Act: -0.1700
Data Index: 4862390 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5189. Min Act: -0.1700
Data Index: 9782180 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5032. Min Act: -0.1700
Data Index: 2713673 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5032. Min Act: -0.1700
Data Index: 1629171 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.5032. Min Act: -0.1700
Data Index: 2811996 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.4876. Min Act: -0.1700
Data Index: 1617722 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.4876. Min Act: -0.1700
Data Index: 2607949 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6442. Min Range: -3.6442
Max Act: 3.4876. Min Act: -0.1700
Data Index: 8986261 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19