Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6423. Min Range: -2.6423

Max Act: 2.6423. Min Act: -0.0000

Data Index: 1242935 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 2.6423. Min Range: -2.6423

Max Act: 2.2981. Min Act: -0.0000

Data Index: 1236199 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 2.6423. Min Range: -2.6423

Max Act: 2.1082. Min Act: -0.0000

Data Index: 1049938 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 2.6423. Min Range: -2.6423

Max Act: 2.0799. Min Act: -0.0000

Data Index: 143527 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.6423. Min Range: -2.6423

Max Act: 2.2189. Min Act: -0.0000

Data Index: 824353 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 2.6423. Min Range: -2.6423

Max Act: 2.1374. Min Act: -0.0000

Data Index: 790483 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.9487. Min Act: -0.0000

Data Index: 380892 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.9704. Min Act: -0.0000

Data Index: 492545 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.8080. Min Act: -0.0000

Data Index: 393575 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7338. Min Act: -0.0000

Data Index: 1270102 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1011024 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7891. Min Act: -0.0000

Data Index: 1279575 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.5589. Min Act: -0.0000

Data Index: 968697 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7347. Min Act: -0.0000

Data Index: 565756 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7391. Min Act: -0.0000

Data Index: 867838 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7398. Min Act: -0.0000

Data Index: 1083750 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.6214. Min Act: -0.0000

Data Index: 539708 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.7174. Min Act: -0.0000

Data Index: 881606 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.5924. Min Act: -0.0000

Data Index: 32970 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 2.6423. Min Range: -2.6423

Max Act: 1.3866. Min Act: -0.0000

Data Index: 462005 (C4 (Web Text))

Max Activating Token Index: 428