Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2203 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2916. Min Act: -0.0001
Data Index: 396843 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2757. Min Act: -0.0001
Data Index: 1244122 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2826. Min Act: -0.0001
Data Index: 1373462 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2912. Min Act: -0.0001
Data Index: 1362116 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2813. Min Act: -0.0001
Data Index: 899373 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2792. Min Act: -0.0001
Data Index: 483730 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2862. Min Act: -0.0001
Data Index: 1152243 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2691. Min Act: -0.0001
Data Index: 346468 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2830. Min Act: -0.0001
Data Index: 1325506 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2705. Min Act: -0.0001
Data Index: 363388 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2717. Min Act: -0.0001
Data Index: 1631386 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2751. Min Act: -0.0001
Data Index: 73470 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2697. Min Act: -0.0001
Data Index: 1291399 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2851. Min Act: -0.0001
Data Index: 546033 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2740. Min Act: -0.0001
Data Index: 341363 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2740. Min Act: -0.0001
Data Index: 1793914 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2494. Min Act: -0.0001
Data Index: 1871954 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2659. Min Act: -0.0001
Data Index: 302369 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2303. Min Act: -0.0001
Data Index: 424445 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2916. Min Range: -0.2916
Max Act: 0.2553. Min Act: -0.0001
Data Index: 810794 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19