Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 628 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0169. Min Act: -0.0001
Data Index: 377626 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0154. Min Act: -0.0001
Data Index: 566497 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0154. Min Act: -0.0001
Data Index: 1552731 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0149. Min Act: -0.0001
Data Index: 647443 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0149. Min Act: -0.0001
Data Index: 442595 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 1034776 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 218262 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 891539 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 37682 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 289678 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 121147 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 178994 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 524723 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 730441 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 268983 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 399102 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 671905 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 925967 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 486309 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0169. Min Range: -0.0169
Max Act: 0.0147. Min Act: -0.0001
Data Index: 845521 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19