Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1895 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2738. Min Range: -2.2738
Max Act: 2.2738. Min Act: -0.0001
Data Index: 513164 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2738. Min Range: -2.2738
Max Act: 2.2067. Min Act: -0.0001
Data Index: 494455 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2738. Min Range: -2.2738
Max Act: 2.0221. Min Act: -0.0001
Data Index: 84784 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.7125. Min Act: -0.0001
Data Index: 1289656 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.5859. Min Act: -0.0001
Data Index: 508460 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.5482. Min Act: -0.0001
Data Index: 687453 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.4158. Min Act: -0.0001
Data Index: 691221 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3378. Min Act: -0.0001
Data Index: 9169 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3909. Min Act: -0.0001
Data Index: 940845 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.4615. Min Act: -0.0001
Data Index: 1326020 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3364. Min Act: -0.0001
Data Index: 1029152 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3720. Min Act: -0.0001
Data Index: 864234 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3878. Min Act: -0.0001
Data Index: 458452 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3886. Min Act: -0.0001
Data Index: 723996 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3409. Min Act: -0.0001
Data Index: 966204 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.2901. Min Act: -0.0001
Data Index: 699320 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.2386. Min Act: -0.0001
Data Index: 697349 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.2851. Min Act: -0.0001
Data Index: 1071178 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.2815. Min Act: -0.0001
Data Index: 532474 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2738. Min Range: -2.2738
Max Act: 1.3902. Min Act: -0.0001
Data Index: 1317056 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19