Model: None
Dataset: The Pile
Neuron 1260 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4629. Min Act: -0.1700
Data Index: 9516504 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4629. Min Act: -0.1700
Data Index: 605473 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4629. Min Act: -0.1700
Data Index: 5959715 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4472. Min Act: -0.1700
Data Index: 7519359 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4472. Min Act: -0.1700
Data Index: 7590519 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4472. Min Act: -0.1700
Data Index: 762478 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4472. Min Act: -0.1700
Data Index: 3920626 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4316. Min Act: -0.1700
Data Index: 8707696 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4316. Min Act: -0.1700
Data Index: 668403 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4316. Min Act: -0.1700
Data Index: 2399192 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4316. Min Act: -0.1700
Data Index: 1664257 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4159. Min Act: -0.1700
Data Index: 9583136 (The Pile)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4159. Min Act: -0.1700
Data Index: 3792994 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4159. Min Act: -0.1700
Data Index: 558558 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4159. Min Act: -0.1700
Data Index: 10358552 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4159. Min Act: -0.1700
Data Index: 9399307 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4159. Min Act: -0.1700
Data Index: 6983627 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4002. Min Act: -0.1700
Data Index: 814938 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4002. Min Act: -0.1700
Data Index: 5047372 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4629. Min Range: -3.4629
Max Act: 3.4002. Min Act: -0.1700
Data Index: 5135027 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19