Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 6 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1267150 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6172. Min Act: -0.0000

Data Index: 846849 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5879. Min Act: 0.0000

Data Index: 744671 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1196308 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5276. Min Act: -0.0000

Data Index: 36068 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4724. Min Act: -0.0000

Data Index: 504042 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1070188 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1133933 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1320834 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4412. Min Act: -0.0000

Data Index: 772845 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4297. Min Act: -0.0000

Data Index: 380411 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4279. Min Act: -0.0000

Data Index: 935372 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4348. Min Act: -0.0000

Data Index: 119760 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4078. Min Act: -0.0000

Data Index: 351248 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4111. Min Act: -0.0000

Data Index: 183231 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.3948. Min Act: -0.0000

Data Index: 206541 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4080. Min Act: -0.0000

Data Index: 758902 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4031. Min Act: -0.0000

Data Index: 577162 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4181. Min Act: -0.0000

Data Index: 843984 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.3870. Min Act: -0.0000

Data Index: 439968 (C4 (Web Text))

Max Activating Token Index: 926