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

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

Neuron 3213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3752. Min Act: -0.0001

Data Index: 1063495 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1347268 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.3422. Min Act: -0.0000

Data Index: 197701 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2979. Min Act: -0.0001

Data Index: 971305 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2910. Min Act: -0.0000

Data Index: 432029 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1344589 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2755. Min Act: -0.0000

Data Index: 499522 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2737. Min Act: -0.0001

Data Index: 1127547 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2511. Min Act: -0.0001

Data Index: 446466 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2594. Min Act: -0.0000

Data Index: 672928 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2468. Min Act: -0.0000

Data Index: 797761 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2376. Min Act: -0.0000

Data Index: 876987 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1286348 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2279. Min Act: -0.0000

Data Index: 378103 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.1879. Min Act: -0.0000

Data Index: 172529 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2179. Min Act: -0.0001

Data Index: 837703 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2342. Min Act: -0.0000

Data Index: 301392 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2128. Min Act: -0.0001

Data Index: 656277 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2025. Min Act: -0.0001

Data Index: 365330 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.3752. Min Range: -0.3752

Max Act: 0.2033. Min Act: -0.0000

Data Index: 38740 (C4 (Web Text))

Max Activating Token Index: 727