Model: None
Dataset: The Pile
Neuron 3353 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.6004. Min Act: -0.1700
Data Index: 6034460 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.6004. Min Act: -0.1700
Data Index: 8849967 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.5843. Min Act: -0.1700
Data Index: 4627857 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.5521. Min Act: -0.1700
Data Index: 423823 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.5359. Min Act: -0.1700
Data Index: 10191490 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.5359. Min Act: -0.1700
Data Index: 1337526 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.5198. Min Act: -0.1695
Data Index: 8111081 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.5198. Min Act: -0.1700
Data Index: 3645142 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4712. Min Act: -0.1700
Data Index: 1197983 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4549. Min Act: -0.1700
Data Index: 5081314 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4549. Min Act: -0.1700
Data Index: 7072236 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4549. Min Act: -0.1700
Data Index: 5185206 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4549. Min Act: -0.1700
Data Index: 1804480 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4549. Min Act: -0.1700
Data Index: 1553611 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4387. Min Act: -0.1668
Data Index: 10170610 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4387. Min Act: -0.1700
Data Index: 5051852 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4387. Min Act: -0.1700
Data Index: 6258167 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4387. Min Act: -0.1684
Data Index: 8727723 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4387. Min Act: -0.1700
Data Index: 8318793 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6004. Min Range: -2.6004
Max Act: 2.4387. Min Act: -0.1700
Data Index: 10404577 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19