Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.6382. Min Act: -0.0000

Data Index: 231262 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.3161. Min Act: -0.0000

Data Index: 459133 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.3613. Min Act: -0.0000

Data Index: 452667 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.3229. Min Act: -0.0001

Data Index: 757195 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2456. Min Act: -0.0001

Data Index: 1132039 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.0420. Min Act: -0.0000

Data Index: 211857 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2108. Min Act: -0.0001

Data Index: 748932 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2689. Min Act: -0.0000

Data Index: 199426 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2964. Min Act: -0.0000

Data Index: 968874 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1099. Min Act: -0.0000

Data Index: 490461 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2188. Min Act: -0.0001

Data Index: 1192920 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2723. Min Act: -0.0001

Data Index: 604643 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1667. Min Act: -0.0000

Data Index: 808676 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1922. Min Act: -0.0001

Data Index: 1226691 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1272. Min Act: -0.0001

Data Index: 907646 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1802. Min Act: -0.0001

Data Index: 440387 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1193639 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1332. Min Act: -0.0001

Data Index: 702628 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.1585. Min Act: -0.0000

Data Index: 837787 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.6382. Min Range: -1.6382

Max Act: 1.2615. Min Act: -0.0000

Data Index: 936594 (C4 (Web Text))

Max Activating Token Index: 608