Model: None
Dataset: The Pile
Neuron 987 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.8448. Min Act: -0.1700
Data Index: 6048225 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.8448. Min Act: -0.1700
Data Index: 5257990 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.8019. Min Act: -0.1700
Data Index: 2441683 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7847. Min Act: -0.1700
Data Index: 3586764 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7675. Min Act: -0.1700
Data Index: 6452256 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7761. Min Act: -0.1700
Data Index: 5534536 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7675. Min Act: -0.1700
Data Index: 3464672 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7761. Min Act: -0.1700
Data Index: 5250127 (The Pile)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7675. Min Act: -0.1700
Data Index: 8653676 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 8060671 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 397021 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 5621892 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7761. Min Act: -0.1700
Data Index: 3578729 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7675. Min Act: -0.1700
Data Index: 6850630 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 6266210 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 6370578 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 1902585 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 2717090 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7675. Min Act: -0.1700
Data Index: 4158354 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8448. Min Range: -1.8448
Max Act: 1.7588. Min Act: -0.1700
Data Index: 2172438 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19