Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1516 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.5230. Min Act: -0.0001
Data Index: 230173 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.5188. Min Act: -0.0001
Data Index: 870223 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.4420. Min Act: -0.0001
Data Index: 1248999 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.4079. Min Act: -0.0001
Data Index: 1557226 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.4178. Min Act: -0.0001
Data Index: 1685900 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3598. Min Act: -0.0001
Data Index: 1912729 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.2667. Min Act: -0.0001
Data Index: 477266 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3585. Min Act: -0.0001
Data Index: 1700230 (The Pile)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3912. Min Act: -0.0001
Data Index: 1554518 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.2011. Min Act: -0.0001
Data Index: 1128823 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3502. Min Act: -0.0001
Data Index: 1920931 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.4111. Min Act: -0.0001
Data Index: 458953 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.4308. Min Act: -0.0001
Data Index: 173072 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3606. Min Act: -0.0001
Data Index: 950141 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.2964. Min Act: -0.0001
Data Index: 1596264 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3706. Min Act: -0.0001
Data Index: 1869588 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.4314. Min Act: -0.0001
Data Index: 741035 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3234. Min Act: -0.0001
Data Index: 645144 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.3552. Min Act: -0.0001
Data Index: 1765963 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5230. Min Range: -1.5230
Max Act: 1.2919. Min Act: -0.0001
Data Index: 663223 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19