Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 238 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2960. Min Act: -0.0001
Data Index: 1887884 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2860. Min Act: -0.0001
Data Index: 1374110 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2788. Min Act: -0.0001
Data Index: 1580315 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2800. Min Act: -0.0001
Data Index: 1053689 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2575. Min Act: -0.0001
Data Index: 1449190 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2755. Min Act: -0.0001
Data Index: 48526 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2642. Min Act: -0.0001
Data Index: 1137048 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2714. Min Act: -0.0001
Data Index: 1927990 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2871. Min Act: -0.0001
Data Index: 1134835 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2553. Min Act: -0.0001
Data Index: 180342 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2649. Min Act: -0.0001
Data Index: 820007 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2712. Min Act: -0.0001
Data Index: 616165 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2796. Min Act: -0.0001
Data Index: 171710 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2497. Min Act: -0.0001
Data Index: 214220 (The Pile)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2544. Min Act: -0.0001
Data Index: 676123 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2546. Min Act: -0.0001
Data Index: 1911951 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2538. Min Act: -0.0001
Data Index: 1163787 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2490. Min Act: -0.0001
Data Index: 392679 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2495. Min Act: -0.0001
Data Index: 220525 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2960. Min Range: -0.2960
Max Act: 0.2482. Min Act: -0.0001
Data Index: 375961 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19