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

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

Neuron 4883 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.9622. Min Act: -0.0000

Data Index: 864451 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.7669. Min Act: -0.0000

Data Index: 1284431 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.8112. Min Act: -0.0000

Data Index: 564605 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.7055. Min Act: -0.0000

Data Index: 508925 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.6238. Min Act: -0.0000

Data Index: 655300 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.7615. Min Act: -0.0000

Data Index: 661646 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1020867 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.5855. Min Act: -0.0000

Data Index: 893515 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.6759. Min Act: -0.0000

Data Index: 328197 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1019725 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.5274. Min Act: -0.0000

Data Index: 525471 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1319547 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.3095. Min Act: -0.0000

Data Index: 125643 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.4781. Min Act: -0.0000

Data Index: 657754 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.3300. Min Act: -0.0000

Data Index: 841881 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.3269. Min Act: -0.0000

Data Index: 663332 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.3649. Min Act: -0.0000

Data Index: 1283879 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.3977. Min Act: -0.0000

Data Index: 989038 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.4189. Min Act: -0.0000

Data Index: 642974 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.9622. Min Range: -1.9622

Max Act: 1.3694. Min Act: -0.0000

Data Index: 522896 (C4 (Web Text))

Max Activating Token Index: 991