Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2638. Min Act: -0.0005

Data Index: 377196 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2602. Min Act: -0.0005

Data Index: 62341 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2459. Min Act: -0.0005

Data Index: 1170469 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2417. Min Act: -0.0005

Data Index: 1245538 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2374. Min Act: -0.0005

Data Index: 1018005 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2419. Min Act: -0.0005

Data Index: 1299775 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2340. Min Act: -0.0005

Data Index: 344418 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2310. Min Act: -0.0005

Data Index: 802193 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2216. Min Act: -0.0005

Data Index: 946252 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2397. Min Act: -0.0005

Data Index: 1174533 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2384. Min Act: -0.0005

Data Index: 1020272 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2195. Min Act: -0.0005

Data Index: 1178395 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2368. Min Act: -0.0005

Data Index: 332905 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2293. Min Act: -0.0005

Data Index: 477012 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2169. Min Act: -0.0005

Data Index: 190520 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2328. Min Act: -0.0005

Data Index: 219904 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2325. Min Act: -0.0005

Data Index: 631494 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2250. Min Act: -0.0005

Data Index: 479218 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2411. Min Act: -0.0005

Data Index: 35425 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2221. Min Act: -0.0005

Data Index: 1274898 (C4 (Web Text))

Max Activating Token Index: 191