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

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

Neuron 5615 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0762. Min Range: -4.0762

Max Act: 4.0762. Min Act: -0.0000

Data Index: 759393 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.9050. Min Act: -0.0000

Data Index: 998410 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.7578. Min Act: -0.0000

Data Index: 869401 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.4076. Min Act: -0.0000

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.2003. Min Act: -0.0000

Data Index: 1207080 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.2211. Min Act: -0.0000

Data Index: 1082889 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.9664. Min Act: -0.0000

Data Index: 1270550 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.1032. Min Act: -0.0000

Data Index: 667154 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.0509. Min Act: -0.0000

Data Index: 915290 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.0369. Min Act: -0.0000

Data Index: 1079032 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 4.0762. Min Range: -4.0762

Max Act: 3.1136. Min Act: -0.0000

Data Index: 202119 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.7277. Min Act: -0.0000

Data Index: 344792 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.8430. Min Act: -0.0000

Data Index: 1141520 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.8397. Min Act: -0.0000

Data Index: 1136937 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.8139. Min Act: -0.0000

Data Index: 1009850 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.7506. Min Act: -0.0000

Data Index: 575404 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.8864. Min Act: -0.0000

Data Index: 1143638 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.7217. Min Act: -0.0000

Data Index: 1009355 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.6038. Min Act: -0.0000

Data Index: 1196954 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 4.0762. Min Range: -4.0762

Max Act: 2.5716. Min Act: -0.0000

Data Index: 141758 (C4 (Web Text))

Max Activating Token Index: 672