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

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

Neuron 4578 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3356. Min Act: -0.0000

Data Index: 472815 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3321. Min Act: -0.0000

Data Index: 320432 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3191. Min Act: -0.0000

Data Index: 468206 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.3170. Min Act: -0.0000

Data Index: 485404 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2620. Min Act: -0.0000

Data Index: 362923 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2620. Min Act: 0.0000

Data Index: 506707 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2498. Min Act: -0.0000

Data Index: 38369 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2647. Min Act: -0.0000

Data Index: 510494 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2741. Min Act: -0.0000

Data Index: 904310 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2633. Min Act: -0.0000

Data Index: 542826 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2526. Min Act: -0.0000

Data Index: 105714 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2598. Min Act: -0.0000

Data Index: 885983 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2593. Min Act: -0.0000

Data Index: 557282 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2473. Min Act: -0.0000

Data Index: 167227 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2448. Min Act: -0.0000

Data Index: 209452 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2487. Min Act: -0.0000

Data Index: 103091 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2412. Min Act: -0.0000

Data Index: 186896 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1260951 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2427. Min Act: -0.0000

Data Index: 968953 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.3356. Min Range: -0.3356

Max Act: 0.2411. Min Act: 0.0000

Data Index: 285653 (C4 (Web Text))

Max Activating Token Index: 367