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

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

Neuron 3133 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: 0.8692. Min Range: -0.8692

Max Act: 0.8692. Min Act: -0.0000

Data Index: 712691 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5557. Min Act: -0.0000

Data Index: 549943 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1162539 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5367. Min Act: -0.0000

Data Index: 207533 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4864. Min Act: -0.0000

Data Index: 830408 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5370. Min Act: -0.0000

Data Index: 565780 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1221358 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4865. Min Act: -0.0000

Data Index: 672980 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4904. Min Act: -0.0000

Data Index: 387340 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4758. Min Act: -0.0000

Data Index: 905956 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4857. Min Act: -0.0000

Data Index: 889761 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4980. Min Act: -0.0000

Data Index: 316833 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4933. Min Act: -0.0000

Data Index: 146221 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1237712 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4535. Min Act: -0.0000

Data Index: 244458 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1225084 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1150317 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4529. Min Act: -0.0000

Data Index: 228667 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1208373 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.8692. Min Range: -0.8692

Max Act: 0.4362. Min Act: -0.0000

Data Index: 900892 (C4 (Web Text))

Max Activating Token Index: 186