Model: None
Dataset: The Pile
Neuron 3939 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.6268. Min Act: -0.1700
Data Index: 3877912 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.5328. Min Act: -0.1700
Data Index: 1849701 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.5172. Min Act: -0.1700
Data Index: 3705062 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4858. Min Act: -0.1700
Data Index: 3930134 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4545. Min Act: -0.1700
Data Index: 4044202 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4388. Min Act: -0.1700
Data Index: 7894667 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4388. Min Act: -0.1700
Data Index: 834307 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4388. Min Act: -0.1700
Data Index: 233311 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4388. Min Act: -0.1700
Data Index: 4675215 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4388. Min Act: -0.1700
Data Index: 1344127 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4231. Min Act: -0.1700
Data Index: 2263206 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4231. Min Act: -0.1700
Data Index: 780810 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4231. Min Act: -0.1700
Data Index: 6099540 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4231. Min Act: -0.1700
Data Index: 5108835 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4231. Min Act: -0.1700
Data Index: 4199781 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4074. Min Act: -0.1700
Data Index: 6892476 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4074. Min Act: -0.1700
Data Index: 3120944 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4074. Min Act: -0.1700
Data Index: 8892982 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4074. Min Act: -0.1700
Data Index: 3433806 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6268. Min Range: -3.6268
Max Act: 3.4074. Min Act: -0.1700
Data Index: 2398797 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19