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

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

Neuron 4306 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1490. Min Range: -1.1490

Max Act: 1.1490. Min Act: -0.0000

Data Index: 331327 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.9910. Min Act: -0.0000

Data Index: 220551 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.9328. Min Act: -0.0000

Data Index: 726342 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8764. Min Act: -0.0000

Data Index: 254401 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1354621 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8057. Min Act: -0.0000

Data Index: 243552 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8508. Min Act: -0.0000

Data Index: 303616 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.7949. Min Act: -0.0000

Data Index: 641074 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8293. Min Act: -0.0000

Data Index: 456620 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8322. Min Act: -0.0000

Data Index: 589557 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8368. Min Act: -0.0000

Data Index: 755844 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8575. Min Act: -0.0000

Data Index: 427186 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8425. Min Act: -0.0000

Data Index: 151998 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8446. Min Act: -0.0000

Data Index: 560338 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8039. Min Act: -0.0000

Data Index: 666072 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8216. Min Act: -0.0000

Data Index: 447052 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8722. Min Act: -0.0000

Data Index: 702749 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8443. Min Act: -0.0000

Data Index: 652850 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.7896. Min Act: -0.0000

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.1490. Min Range: -1.1490

Max Act: 0.8115. Min Act: -0.0000

Data Index: 25595 (C4 (Web Text))

Max Activating Token Index: 549