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

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

Neuron 1031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.7537. Min Act: -0.0001

Data Index: 877263 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.6365. Min Act: -0.0001

Data Index: 1066137 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.6983. Min Act: -0.0001

Data Index: 768388 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3636. Min Act: -0.0002

Data Index: 353158 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.4024. Min Act: -0.0001

Data Index: 19400 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3944. Min Act: -0.0002

Data Index: 1338822 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.4619. Min Act: -0.0002

Data Index: 97999 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.4168. Min Act: -0.0001

Data Index: 704860 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.1866. Min Act: -0.0001

Data Index: 598530 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3869. Min Act: -0.0001

Data Index: 490190 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.4221. Min Act: -0.0001

Data Index: 816239 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3458. Min Act: -0.0002

Data Index: 390227 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3157. Min Act: -0.0002

Data Index: 442857 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3485. Min Act: -0.0002

Data Index: 887907 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3497. Min Act: -0.0002

Data Index: 132720 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.2478. Min Act: -0.0001

Data Index: 801164 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.2539. Min Act: -0.0001

Data Index: 1162393 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3892. Min Act: -0.0001

Data Index: 690792 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.3205. Min Act: -0.0002

Data Index: 1051850 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.7537. Min Range: -1.7537

Max Act: 1.2749. Min Act: -0.0001

Data Index: 296904 (C4 (Web Text))

Max Activating Token Index: 652