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

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

Neuron 5301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2622. Min Act: -0.0000

Data Index: 822469 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2399. Min Act: -0.0000

Data Index: 664924 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2386. Min Act: -0.0000

Data Index: 321198 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2553. Min Act: -0.0000

Data Index: 570882 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2365. Min Act: -0.0000

Data Index: 853128 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2521. Min Act: -0.0000

Data Index: 918066 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2361. Min Act: -0.0000

Data Index: 16672 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2352. Min Act: -0.0000

Data Index: 889240 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2327. Min Act: -0.0000

Data Index: 783658 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2422. Min Act: -0.0000

Data Index: 207342 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2289. Min Act: -0.0000

Data Index: 8514 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2343. Min Act: -0.0000

Data Index: 819070 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2111. Min Act: -0.0000

Data Index: 587399 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2177. Min Act: -0.0000

Data Index: 776307 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2165. Min Act: -0.0000

Data Index: 743738 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2155. Min Act: -0.0000

Data Index: 915048 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2189. Min Act: -0.0000

Data Index: 745787 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2173. Min Act: -0.0000

Data Index: 836368 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2313. Min Act: -0.0000

Data Index: 831029 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2248. Min Act: -0.0000

Data Index: 630838 (C4 (Web Text))

Max Activating Token Index: 545