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

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

Neuron 5929 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.3730. Min Act: -0.0000

Data Index: 1095894 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.3766. Min Act: -0.0000

Data Index: 724481 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.3288. Min Act: -0.0000

Data Index: 296700 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1170529 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1578. Min Act: -0.0000

Data Index: 177893 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.3276. Min Act: -0.0000

Data Index: 364790 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.2240. Min Act: -0.0000

Data Index: 247244 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.2306. Min Act: -0.0000

Data Index: 13875 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1608790 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.2045. Min Act: -0.0000

Data Index: 587294 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1480940 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1611699 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1741. Min Act: -0.0000

Data Index: 263280 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.2186. Min Act: -0.0000

Data Index: 258996 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1021744 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1770. Min Act: -0.0000

Data Index: 468249 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1278095 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1249. Min Act: -0.0000

Data Index: 1264200 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1622. Min Act: -0.0000

Data Index: 832609 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.3766. Min Range: -1.3766

Max Act: 1.1223. Min Act: -0.0000

Data Index: 483737 (C4 (Web Text))

Max Activating Token Index: 808