Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2032 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.4446. Min Act: -0.0001
Data Index: 1331130 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.2962. Min Act: -0.0001
Data Index: 450824 (The Pile)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.2420. Min Act: -0.0001
Data Index: 446591 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.2421. Min Act: -0.0001
Data Index: 338300 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1914. Min Act: -0.0001
Data Index: 501753 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1189. Min Act: -0.0001
Data Index: 1653208 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.2154. Min Act: -0.0001
Data Index: 1571766 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.2041. Min Act: -0.0001
Data Index: 1776587 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1564. Min Act: -0.0001
Data Index: 175138 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1747. Min Act: -0.0001
Data Index: 751019 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1486. Min Act: -0.0001
Data Index: 242563 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0825. Min Act: -0.0001
Data Index: 1704364 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0376. Min Act: -0.0001
Data Index: 881189 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1943. Min Act: -0.0001
Data Index: 1276154 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0370. Min Act: -0.0001
Data Index: 1612659 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0713. Min Act: -0.0001
Data Index: 479475 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0904. Min Act: -0.0001
Data Index: 1002326 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.1161. Min Act: -0.0001
Data Index: 386723 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0667. Min Act: -0.0001
Data Index: 161198 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4446. Min Range: -1.4446
Max Act: 1.0617. Min Act: -0.0001
Data Index: 707845 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19