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

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

Neuron 1331 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1275 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.1107. Min Act: -0.0000

Data Index: 797734 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.1056. Min Act: 0.0000

Data Index: 798777 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0889. Min Act: -0.0000

Data Index: 695274 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1230147 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0744. Min Act: -0.0000

Data Index: 482887 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0250. Min Act: -0.0000

Data Index: 236842 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0242. Min Act: -0.0000

Data Index: 670042 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0257. Min Act: -0.0000

Data Index: 7213 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0190. Min Act: -0.0000

Data Index: 201482 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0536. Min Act: -0.0000

Data Index: 934509 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9861. Min Act: -0.0000

Data Index: 486767 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9808. Min Act: -0.0000

Data Index: 7164 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9726. Min Act: 0.0000

Data Index: 166989 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9718. Min Act: 0.0002

Data Index: 791271 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9761. Min Act: -0.0000

Data Index: 632460 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 1.1611. Min Range: -1.1611

Max Act: 1.0306. Min Act: 0.0000

Data Index: 1068725 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9633. Min Act: -0.0000

Data Index: 660888 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9375. Min Act: -0.0000

Data Index: 993541 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 1.1611. Min Range: -1.1611

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1267280 (C4 (Web Text))

Max Activating Token Index: 964