Model: None
Dataset: The Pile
Neuron 1154 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.9556. Min Act: -0.1700
Data Index: 621844 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.9239. Min Act: -0.1700
Data Index: 5876312 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.9080. Min Act: -0.1665
Data Index: 507106 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8922. Min Act: -0.1700
Data Index: 2480992 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8763. Min Act: -0.1665
Data Index: 7060461 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8604. Min Act: -0.1665
Data Index: 863158 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8445. Min Act: -0.1700
Data Index: 1768385 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8445. Min Act: -0.1700
Data Index: 550935 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8445. Min Act: -0.1700
Data Index: 934723 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8445. Min Act: -0.1700
Data Index: 9818008 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8445. Min Act: -0.1700
Data Index: 8908557 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8286. Min Act: -0.1700
Data Index: 9477728 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8127. Min Act: -0.1665
Data Index: 615079 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.8127. Min Act: -0.1677
Data Index: 9743188 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.7968. Min Act: -0.1700
Data Index: 5286939 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.7968. Min Act: -0.1699
Data Index: 10485413 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.7968. Min Act: -0.1700
Data Index: 4050034 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.7968. Min Act: -0.1700
Data Index: 2015559 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.7968. Min Act: -0.1700
Data Index: 3856317 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9556. Min Range: -2.9556
Max Act: 2.7968. Min Act: -0.1700
Data Index: 9366487 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19