Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1176 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0040. Min Range: -1.0040
Max Act: 1.0040. Min Act: -0.0001
Data Index: 1336558 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8881. Min Act: -0.0001
Data Index: 161641 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.9211. Min Act: -0.0001
Data Index: 296384 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.9559. Min Act: -0.0001
Data Index: 631463 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8991. Min Act: -0.0001
Data Index: 1637428 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8972. Min Act: -0.0001
Data Index: 671758 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8203. Min Act: -0.0001
Data Index: 1429006 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.7873. Min Act: -0.0001
Data Index: 503742 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8242. Min Act: -0.0001
Data Index: 821905 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8364. Min Act: -0.0001
Data Index: 685245 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8332. Min Act: -0.0001
Data Index: 1060801 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.7958. Min Act: -0.0001
Data Index: 1885407 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.7536. Min Act: -0.0001
Data Index: 1265816 (The Pile)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.7551. Min Act: -0.0001
Data Index: 399960 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8046. Min Act: -0.0001
Data Index: 825883 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8164. Min Act: -0.0001
Data Index: 1638411 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.7823. Min Act: -0.0001
Data Index: 712456 (The Pile)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.7181. Min Act: -0.0001
Data Index: 1071698 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.8083. Min Act: -0.0001
Data Index: 319618 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0040. Min Range: -1.0040
Max Act: 0.6933. Min Act: -0.0001
Data Index: 1868562 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19