Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.8616. Min Act: -0.0001
Data Index: 1867142 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.6958. Min Act: -0.0001
Data Index: 1510319 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.7097. Min Act: -0.0001
Data Index: 965202 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.7154. Min Act: -0.0000
Data Index: 1145259 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.6165. Min Act: -0.0000
Data Index: 1079659 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.5862. Min Act: -0.0001
Data Index: 121820 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.7606. Min Act: -0.0001
Data Index: 576659 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.5365. Min Act: -0.0001
Data Index: 1066004 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.3665. Min Act: -0.0001
Data Index: 1541131 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.1415. Min Act: -0.0001
Data Index: 1110130 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.4401. Min Act: -0.0001
Data Index: 474105 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.5817. Min Act: -0.0001
Data Index: 532847 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.2009. Min Act: -0.0001
Data Index: 577024 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.3456. Min Act: -0.0001
Data Index: 1950914 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.1262. Min Act: -0.0001
Data Index: 1776338 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.2643. Min Act: -0.0001
Data Index: 788126 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.2009. Min Act: -0.0001
Data Index: 1097876 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8616. Min Range: -4.8616
Max Act: 4.1544. Min Act: -0.0001
Data Index: 1444897 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8616. Min Range: -4.8616
Max Act: 3.9701. Min Act: -0.0001
Data Index: 1323669 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8616. Min Range: -4.8616
Max Act: 3.4912. Min Act: -0.0001
Data Index: 1574430 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19