Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 5106 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.1408. Min Range: -2.1408
Max Act: 2.1129. Min Act: -0.0000
Data Index: 429747 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1408. Min Range: -2.1408
Max Act: 2.1180. Min Act: -0.0000
Data Index: 1853272 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1408. Min Range: -2.1408
Max Act: 2.1408. Min Act: -0.0000
Data Index: 1663881 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1408. Min Range: -2.1408
Max Act: 2.0285. Min Act: -0.0000
Data Index: 509748 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 586111 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 583270 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 551216 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 6913 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 161891 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 529195 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 518799 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 250195 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 505629 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 459953 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 55418 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 406671 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 346231 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 448478 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 439524 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1408. Min Range: -2.1408
Max Act: 1.8916. Min Act: -0.0000
Data Index: 194433 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19