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

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

Neuron 647 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0450. Min Act: -0.0006

Data Index: 1283151 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0006

Data Index: 996019 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0395. Min Act: -0.0006

Data Index: 645257 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0376. Min Act: -0.0006

Data Index: 493112 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0371. Min Act: -0.0006

Data Index: 354631 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0350. Min Act: -0.0006

Data Index: 441268 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1034835 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0353. Min Act: -0.0006

Data Index: 933196 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1318882 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1060834 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0348. Min Act: -0.0006

Data Index: 502120 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1343575 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0345. Min Act: -0.0006

Data Index: 811917 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1062868 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0337. Min Act: -0.0006

Data Index: 637541 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0338. Min Act: -0.0006

Data Index: 559916 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1099001 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0331. Min Act: -0.0006

Data Index: 786900 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0333. Min Act: -0.0006

Data Index: 613611 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1060417 (C4 (Web Text))

Max Activating Token Index: 911