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

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

Neuron 432 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.4234. Min Act: -0.0000

Data Index: 414688 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3404. Min Act: -0.0000

Data Index: 651528 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3451. Min Act: -0.0000

Data Index: 446608 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1291338 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3322. Min Act: -0.0000

Data Index: 491640 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3387. Min Act: -0.0000

Data Index: 135521 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1166648 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.3319. Min Act: -0.0000

Data Index: 13438 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2943. Min Act: -0.0000

Data Index: 628514 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1031970 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2533. Min Act: -0.0000

Data Index: 183680 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1056425 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2520. Min Act: -0.0000

Data Index: 429756 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2393. Min Act: -0.0000

Data Index: 141707 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2496. Min Act: -0.0000

Data Index: 938098 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1337297 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2402. Min Act: -0.0000

Data Index: 784555 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2637. Min Act: -0.0000

Data Index: 780802 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2425. Min Act: -0.0000

Data Index: 301195 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.4234. Min Range: -0.4234

Max Act: 0.2179. Min Act: -0.0000

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 780