Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2516 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 10.0296. Min Range: -10.0296
Max Act: 10.0296. Min Act: 0.0010
Data Index: 1121946 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.3351. Min Act: 0.0003
Data Index: 1386988 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.2810. Min Act: 0.0010
Data Index: 464830 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.6559. Min Act: 0.0010
Data Index: 858548 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.0017. Min Act: 0.0010
Data Index: 704567 (The Pile)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.8143. Min Act: 0.0010
Data Index: 287418 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.3444. Min Act: 0.0010
Data Index: 1617110 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.4267. Min Act: 0.0007
Data Index: 1825153 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.7681. Min Act: 0.0010
Data Index: 1696364 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.0956. Min Act: 0.0010
Data Index: 1185333 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.1842. Min Act: 0.0010
Data Index: 1140298 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.5767. Min Act: 0.0010
Data Index: 849992 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.8733. Min Act: 0.0007
Data Index: 605020 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.9664. Min Act: 0.0010
Data Index: 917268 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.5543. Min Act: -0.0000
Data Index: 716929 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0296. Min Range: -10.0296
Max Act: 9.2089. Min Act: 0.0010
Data Index: 1357410 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.8408. Min Act: 0.0010
Data Index: 124751 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.1443. Min Act: 0.0010
Data Index: 677628 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.3214. Min Act: 0.0010
Data Index: 445428 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0296. Min Range: -10.0296
Max Act: 8.8413. Min Act: 0.0010
Data Index: 1204190 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19