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

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

Neuron 646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.7559. Min Act: -0.0000

Data Index: 229062 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.5341. Min Act: -0.0000

Data Index: 724381 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1171307 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3920. Min Act: -0.0000

Data Index: 426342 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.4280. Min Act: -0.0000

Data Index: 691566 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3908. Min Act: -0.0000

Data Index: 714404 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3763. Min Act: -0.0000

Data Index: 386356 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3622. Min Act: -0.0000

Data Index: 198255 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.3420. Min Act: -0.0000

Data Index: 768075 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2919. Min Act: -0.0000

Data Index: 791376 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1352274 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1927. Min Act: -0.0000

Data Index: 601513 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1875. Min Act: -0.0000

Data Index: 949602 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1230186 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1165. Min Act: -0.0000

Data Index: 393733 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1012. Min Act: -0.0000

Data Index: 471240 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.0610. Min Act: -0.0000

Data Index: 858649 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.1010. Min Act: -0.0000

Data Index: 305374 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 1.7559. Min Range: -1.7559

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1329783 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.7559. Min Range: -1.7559

Max Act: 0.9427. Min Act: -0.0000

Data Index: 892897 (C4 (Web Text))

Max Activating Token Index: 975