Model: None
Dataset: The Pile
Neuron 1308 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.6998. Min Act: -0.1700
Data Index: 7024831 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.6196. Min Act: -0.1700
Data Index: 8751035 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5874. Min Act: -0.1700
Data Index: 10557930 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.6035. Min Act: -0.1700
Data Index: 6206411 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5713. Min Act: -0.1700
Data Index: 7598193 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5713. Min Act: -0.1700
Data Index: 743349 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5552. Min Act: -0.1700
Data Index: 683206 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5552. Min Act: -0.1700
Data Index: 7389671 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5552. Min Act: -0.1700
Data Index: 1420626 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5552. Min Act: -0.1700
Data Index: 593376 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5390. Min Act: -0.1700
Data Index: 9280966 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5390. Min Act: -0.1700
Data Index: 7999946 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5067. Min Act: -0.1700
Data Index: 9501911 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5229. Min Act: -0.1700
Data Index: 9007238 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5390. Min Act: -0.1700
Data Index: 8685851 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5229. Min Act: -0.1700
Data Index: 8601129 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5229. Min Act: -0.1700
Data Index: 256089 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5229. Min Act: -0.1700
Data Index: 4389234 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5067. Min Act: -0.1700
Data Index: 409230 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6998. Min Range: -2.6998
Max Act: 2.5067. Min Act: -0.1700
Data Index: 1303384 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19