Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2875 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.1085. Min Act: -0.0002
Data Index: 203691 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.1167. Min Act: -0.0002
Data Index: 1270871 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.1064. Min Act: -0.0003
Data Index: 1493845 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.1000. Min Act: -0.0002
Data Index: 1124892 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0855. Min Act: -0.0002
Data Index: 997613 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0816. Min Act: -0.0002
Data Index: 1381269 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0831. Min Act: -0.0002
Data Index: 460923 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0856. Min Act: -0.0002
Data Index: 1962527 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0820. Min Act: -0.0002
Data Index: 965108 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0798. Min Act: -0.0003
Data Index: 1546550 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0814. Min Act: -0.0003
Data Index: 954719 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0795. Min Act: -0.0003
Data Index: 248452 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0801. Min Act: -0.0003
Data Index: 523217 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0746. Min Act: -0.0003
Data Index: 889410 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0846. Min Act: -0.0003
Data Index: 1708362 (The Pile)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0777. Min Act: -0.0003
Data Index: 1786293 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0754. Min Act: -0.0002
Data Index: 400708 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0764. Min Act: -0.0002
Data Index: 220939 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0806. Min Act: -0.0003
Data Index: 1911235 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1167. Min Range: -0.1167
Max Act: 0.0779. Min Act: -0.0002
Data Index: 601802 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19