Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2288 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.0165. Min Range: -1.0165
Max Act: 1.0165. Min Act: -0.0002
Data Index: 104915 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.8077. Min Act: -0.0002
Data Index: 1034844 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7765. Min Act: -0.0002
Data Index: 477942 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7954. Min Act: -0.0002
Data Index: 396701 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.8011. Min Act: -0.0002
Data Index: 1399284 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.8774. Min Act: -0.0002
Data Index: 436171 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7890. Min Act: -0.0002
Data Index: 1389806 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7378. Min Act: -0.0002
Data Index: 367655 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7452. Min Act: -0.0002
Data Index: 1541688 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7523. Min Act: -0.0002
Data Index: 134153 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6796. Min Act: -0.0002
Data Index: 367477 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6949. Min Act: -0.0002
Data Index: 334701 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7439. Min Act: -0.0002
Data Index: 1928388 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6673. Min Act: -0.0002
Data Index: 1411474 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.7138. Min Act: -0.0002
Data Index: 524103 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6881. Min Act: -0.0002
Data Index: 642560 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6837. Min Act: -0.0002
Data Index: 807430 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6801. Min Act: -0.0002
Data Index: 631767 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6741. Min Act: -0.0002
Data Index: 400512 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0165. Min Range: -1.0165
Max Act: 0.6112. Min Act: -0.0002
Data Index: 1089333 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19