Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0378. Min Range: -1.0378

Max Act: 1.0098. Min Act: -0.0001

Data Index: 350501 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.0378. Min Range: -1.0378

Max Act: 1.0378. Min Act: -0.0001

Data Index: 840600 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.0378. Min Range: -1.0378

Max Act: 1.0089. Min Act: -0.0001

Data Index: 1325236 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9570. Min Act: -0.0001

Data Index: 1297754 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8881. Min Act: -0.0001

Data Index: 666646 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8374. Min Act: -0.0001

Data Index: 961688 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8489. Min Act: -0.0001

Data Index: 814055 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8391. Min Act: -0.0001

Data Index: 821631 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7272. Min Act: -0.0001

Data Index: 978679 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7619. Min Act: -0.0001

Data Index: 1070639 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8100. Min Act: -0.0001

Data Index: 232117 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7722. Min Act: -0.0001

Data Index: 90835 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7623. Min Act: -0.0001

Data Index: 234405 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8192. Min Act: -0.0001

Data Index: 65553 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8360. Min Act: -0.0001

Data Index: 1001696 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1126318 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7538. Min Act: -0.0001

Data Index: 493727 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7352. Min Act: -0.0001

Data Index: 812652 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7197. Min Act: -0.0001

Data Index: 967126 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7218. Min Act: -0.0001

Data Index: 1155504 (C4 (Web Text))

Max Activating Token Index: 288