Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3827 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 6.2684. Min Range: -6.2684
Max Act: 6.1364. Min Act: -0.0001
Data Index: 956693 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.8021. Min Act: -0.0001
Data Index: 326064 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2684. Min Range: -6.2684
Max Act: 6.2684. Min Act: -0.0001
Data Index: 457294 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.9046. Min Act: -0.0001
Data Index: 996514 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.5361. Min Act: -0.0001
Data Index: 640775 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.8294. Min Act: -0.0001
Data Index: 23356 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.2436. Min Act: -0.0001
Data Index: 410705 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.6891. Min Act: -0.0001
Data Index: 612220 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.4974. Min Act: -0.0001
Data Index: 590551 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.2621. Min Act: -0.0001
Data Index: 1035114 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.2303. Min Act: -0.0001
Data Index: 636637 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.4167. Min Act: -0.0001
Data Index: 243532 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.6487. Min Act: -0.0001
Data Index: 316664 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.3564. Min Act: -0.0001
Data Index: 995363 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.0493. Min Act: -0.0001
Data Index: 1206972 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.3490. Min Act: -0.0001
Data Index: 12315 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.0573. Min Act: -0.0001
Data Index: 1261833 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.1297. Min Act: -0.0001
Data Index: 365938 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2684. Min Range: -6.2684
Max Act: 5.1011. Min Act: -0.0001
Data Index: 11889 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2684. Min Range: -6.2684
Max Act: 4.7360. Min Act: -0.0001
Data Index: 868393 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19