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

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

Neuron 1914 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8370. Min Act: -0.0000

Data Index: 266191 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8825. Min Act: -0.0000

Data Index: 525154 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8462. Min Act: -0.0000

Data Index: 438935 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.8234. Min Act: -0.0000

Data Index: 924997 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7536. Min Act: -0.0000

Data Index: 801199 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7962. Min Act: -0.0000

Data Index: 722630 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.7074. Min Act: -0.0000

Data Index: 714020 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6547. Min Act: -0.0000

Data Index: 55527 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1019713 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1029449 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6714. Min Act: -0.0000

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6992. Min Act: -0.0000

Data Index: 965699 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.5990. Min Act: -0.0000

Data Index: 526223 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1119792 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6535. Min Act: -0.0000

Data Index: 678628 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6224. Min Act: -0.0000

Data Index: 44606 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6967. Min Act: -0.0000

Data Index: 171019 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6163. Min Act: -0.0000

Data Index: 195810 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6609. Min Act: -0.0000

Data Index: 505326 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.8825. Min Range: -0.8825

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1267802 (C4 (Web Text))

Max Activating Token Index: 148