Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2863 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.9371. Min Act: -0.0001
Data Index: 432109 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.7744. Min Act: -0.0001
Data Index: 552990 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.8709. Min Act: -0.0001
Data Index: 406920 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.7311. Min Act: -0.0001
Data Index: 407662 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.8498. Min Act: -0.0001
Data Index: 1046600 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.5765. Min Act: -0.0001
Data Index: 342692 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.6019. Min Act: -0.0001
Data Index: 892482 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.5701. Min Act: -0.0001
Data Index: 1156530 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.5050. Min Act: -0.0001
Data Index: 1334473 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.3546. Min Act: -0.0001
Data Index: 592824 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.5740. Min Act: -0.0001
Data Index: 1051696 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.4506. Min Act: -0.0001
Data Index: 1006086 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.2861. Min Act: -0.0001
Data Index: 372351 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.2501. Min Act: -0.0001
Data Index: 50607 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.4701. Min Act: -0.0001
Data Index: 798474 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.3119. Min Act: -0.0001
Data Index: 941732 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.4462. Min Act: -0.0001
Data Index: 73003 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.4133. Min Act: -0.0001
Data Index: 1317028 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.2807. Min Act: -0.0001
Data Index: 671234 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9371. Min Range: -2.9371
Max Act: 2.2391. Min Act: -0.0001
Data Index: 350374 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19