Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2950. Min Act: -0.0000

Data Index: 997173 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2490. Min Act: -0.0000

Data Index: 801469 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1067287 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2514. Min Act: -0.0001

Data Index: 445943 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2432. Min Act: -0.0000

Data Index: 167914 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2446. Min Act: -0.0000

Data Index: 634422 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1086241 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2352. Min Act: -0.0000

Data Index: 83686 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2313. Min Act: -0.0000

Data Index: 327697 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2239. Min Act: -0.0001

Data Index: 936302 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1298554 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2370. Min Act: -0.0001

Data Index: 832889 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2219. Min Act: -0.0000

Data Index: 809027 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2217. Min Act: -0.0001

Data Index: 759399 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2281. Min Act: -0.0000

Data Index: 31849 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2271. Min Act: -0.0000

Data Index: 980440 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2244. Min Act: -0.0000

Data Index: 98981 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2239. Min Act: -0.0001

Data Index: 930975 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2222. Min Act: -0.0001

Data Index: 376417 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.2950. Min Range: -0.2950

Max Act: 0.2145. Min Act: -0.0000

Data Index: 701921 (C4 (Web Text))

Max Activating Token Index: 790