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

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

Neuron 1988 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: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1233857 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1059212 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1233354 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2337. Min Act: -0.0001

Data Index: 1159474 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2173. Min Act: -0.0000

Data Index: 124852 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1171717 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2083. Min Act: -0.0000

Data Index: 881795 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1832. Min Act: -0.0000

Data Index: 447184 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1958. Min Act: -0.0000

Data Index: 644376 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1875. Min Act: -0.0001

Data Index: 512270 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1778. Min Act: -0.0001

Data Index: 755106 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1269058 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1761. Min Act: -0.0000

Data Index: 860134 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1761. Min Act: -0.0000

Data Index: 835512 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1004215 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1697. Min Act: -0.0001

Data Index: 255753 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1058555 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1053898 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1236973 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1674. Min Act: -0.0001

Data Index: 335671 (C4 (Web Text))

Max Activating Token Index: 823