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

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

Neuron 114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4494. Min Range: -5.4494

Max Act: 5.4494. Min Act: -0.0000

Data Index: 628590 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.5399. Min Act: -0.0000

Data Index: 767207 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.5216. Min Act: -0.0000

Data Index: 982448 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.5335. Min Act: -0.0000

Data Index: 372966 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.4924. Min Act: -0.0000

Data Index: 437316 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.2445. Min Act: -0.0000

Data Index: 1168010 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.0126. Min Act: -0.0000

Data Index: 266734 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.2209. Min Act: -0.0000

Data Index: 579488 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.0690. Min Act: -0.0000

Data Index: 1231490 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.8624. Min Act: -0.0000

Data Index: 766678 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.0309. Min Act: -0.0000

Data Index: 1334098 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.1313. Min Act: -0.0000

Data Index: 312960 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.8131. Min Act: -0.0000

Data Index: 285102 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.9059. Min Act: -0.0000

Data Index: 840898 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.7041. Min Act: -0.0000

Data Index: 979292 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.7487. Min Act: -0.0000

Data Index: 828319 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.0551. Min Act: -0.0000

Data Index: 684547 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.0611. Min Act: -0.0000

Data Index: 1151799 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.5357. Min Act: -0.0000

Data Index: 1297356 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.7961. Min Act: -0.0000

Data Index: 752373 (C4 (Web Text))

Max Activating Token Index: 596