Model: None
Dataset: The Pile
Neuron 2470 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.8678. Min Act: -0.1700
Data Index: 10242587 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.8522. Min Act: -0.1700
Data Index: 3755669 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.8209. Min Act: -0.1700
Data Index: 609389 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.7740. Min Act: -0.1700
Data Index: 916623 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.7584. Min Act: -0.1700
Data Index: 6888765 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.7271. Min Act: -0.1700
Data Index: 985144 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6958. Min Act: -0.1700
Data Index: 7316940 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6801. Min Act: -0.1700
Data Index: 96874 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6645. Min Act: -0.1700
Data Index: 6916387 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6488. Min Act: -0.1700
Data Index: 6262779 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6488. Min Act: -0.1700
Data Index: 923193 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6488. Min Act: -0.1700
Data Index: 4477971 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6488. Min Act: -0.1700
Data Index: 6446835 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6332. Min Act: -0.1700
Data Index: 3587142 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6332. Min Act: -0.1700
Data Index: 2344607 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6332. Min Act: -0.1700
Data Index: 56697 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6332. Min Act: -0.1700
Data Index: 10734121 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6175. Min Act: -0.1700
Data Index: 1984309 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6175. Min Act: -0.1700
Data Index: 3155955 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8678. Min Range: -3.8678
Max Act: 3.6175. Min Act: -0.1700
Data Index: 8490362 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19