Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 568 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.8756. Min Act: -0.0001
Data Index: 31605 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.6740. Min Act: -0.0001
Data Index: 1293496 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.6073. Min Act: -0.0001
Data Index: 1390064 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.4391. Min Act: -0.0001
Data Index: 1685158 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.5288. Min Act: -0.0001
Data Index: 1030966 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.4055. Min Act: -0.0001
Data Index: 687484 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.5099. Min Act: -0.0001
Data Index: 746404 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.4224. Min Act: -0.0001
Data Index: 1818906 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.1523. Min Act: -0.0001
Data Index: 374337 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.2989. Min Act: -0.0001
Data Index: 788064 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.4628. Min Act: -0.0001
Data Index: 753676 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.2847. Min Act: -0.0001
Data Index: 1800537 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.2865. Min Act: -0.0001
Data Index: 1492435 (The Pile)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.4641. Min Act: -0.0001
Data Index: 1529922 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.4022. Min Act: -0.0001
Data Index: 1353384 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.3011. Min Act: -0.0001
Data Index: 1221073 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.1666. Min Act: -0.0001
Data Index: 178082 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.3054. Min Act: -0.0001
Data Index: 412274 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.3567. Min Act: -0.0001
Data Index: 1322799 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8756. Min Range: -1.8756
Max Act: 1.3801. Min Act: -0.0001
Data Index: 921608 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19