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

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

Neuron 5522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1879. Min Range: -1.1879

Max Act: 1.1879. Min Act: -0.0001

Data Index: 419036 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.1879. Min Range: -1.1879

Max Act: 1.1247. Min Act: -0.0001

Data Index: 1162778 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9070. Min Act: -0.0001

Data Index: 298234 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9326. Min Act: -0.0001

Data Index: 826534 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9717. Min Act: -0.0001

Data Index: 949132 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9248. Min Act: -0.0001

Data Index: 638411 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.1879. Min Range: -1.1879

Max Act: 1.0060. Min Act: -0.0001

Data Index: 266724 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1170434 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.1879. Min Range: -1.1879

Max Act: 1.0029. Min Act: -0.0001

Data Index: 5077 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.8820. Min Act: -0.0001

Data Index: 861968 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9037. Min Act: -0.0001

Data Index: 1209866 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.8786. Min Act: -0.0001

Data Index: 625149 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.7927. Min Act: -0.0001

Data Index: 163746 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.8825. Min Act: -0.0001

Data Index: 727067 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.8749. Min Act: -0.0001

Data Index: 86651 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9479. Min Act: -0.0001

Data Index: 914106 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1545023 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.9083. Min Act: -0.0001

Data Index: 3584 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.8195. Min Act: -0.0001

Data Index: 826843 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.1879. Min Range: -1.1879

Max Act: 0.8597. Min Act: -0.0001

Data Index: 908320 (C4 (Web Text))

Max Activating Token Index: 200