Model: None
Dataset: The Pile
Neuron 1307 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4746. Min Act: -0.1700
Data Index: 1864742 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4746. Min Act: -0.1700
Data Index: 9957483 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4746. Min Act: -0.1700
Data Index: 3573168 (The Pile)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4432. Min Act: -0.1700
Data Index: 5217849 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4275. Min Act: -0.1700
Data Index: 8466365 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4118. Min Act: -0.1700
Data Index: 3257164 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.4118. Min Act: -0.1700
Data Index: 7097626 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3805. Min Act: -0.1700
Data Index: 1811299 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3805. Min Act: -0.1700
Data Index: 4614096 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3648. Min Act: -0.1700
Data Index: 7943289 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3648. Min Act: -0.1700
Data Index: 9194553 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3334. Min Act: -0.1700
Data Index: 6103021 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3334. Min Act: -0.1700
Data Index: 2498029 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3177. Min Act: -0.1700
Data Index: 6811494 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3177. Min Act: -0.1700
Data Index: 887254 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3177. Min Act: -0.1700
Data Index: 10016959 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.3020. Min Act: -0.1700
Data Index: 2666478 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.2863. Min Act: -0.1700
Data Index: 4948933 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.2863. Min Act: -0.1700
Data Index: 9812826 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4746. Min Range: -3.4746
Max Act: 3.2863. Min Act: -0.1700
Data Index: 5912569 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19