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

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

Neuron 3180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1947. Min Act: -0.0001

Data Index: 1310444 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2785. Min Act: -0.0001

Data Index: 233480 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.3217. Min Act: -0.0001

Data Index: 1026057 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1809. Min Act: -0.0001

Data Index: 1162015 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.3068. Min Act: -0.0001

Data Index: 805124 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.4454. Min Act: -0.0001

Data Index: 696526 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2835. Min Act: -0.0001

Data Index: 822120 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1348. Min Act: -0.0001

Data Index: 115758 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2950. Min Act: -0.0001

Data Index: 11492 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2329. Min Act: -0.0001

Data Index: 1145700 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2506. Min Act: -0.0001

Data Index: 887392 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2557. Min Act: -0.0001

Data Index: 1024494 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2700. Min Act: -0.0001

Data Index: 812461 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1356. Min Act: -0.0001

Data Index: 1172344 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1371. Min Act: -0.0001

Data Index: 465332 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1528. Min Act: -0.0001

Data Index: 207127 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2187. Min Act: -0.0001

Data Index: 432300 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1093. Min Act: -0.0001

Data Index: 1135635 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1090. Min Act: -0.0001

Data Index: 648062 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1717. Min Act: -0.0001

Data Index: 87802 (C4 (Web Text))

Max Activating Token Index: 81