Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2036 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0005

Data Index: 246705 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0227. Min Act: -0.0005

Data Index: 1043803 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0227. Min Act: -0.0005

Data Index: 1234589 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0224. Min Act: -0.0005

Data Index: 1238933 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0236. Min Act: -0.0005

Data Index: 187647 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1166948 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0213. Min Act: -0.0005

Data Index: 1230362 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0215. Min Act: -0.0005

Data Index: 1129313 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0203. Min Act: -0.0005

Data Index: 182294 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0198. Min Act: -0.0005

Data Index: 354296 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0227. Min Act: -0.0005

Data Index: 243142 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1154310 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0209. Min Act: -0.0005

Data Index: 975474 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0209. Min Act: -0.0005

Data Index: 1336655 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1022074 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0211. Min Act: -0.0005

Data Index: 202916 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1022762 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0211. Min Act: -0.0005

Data Index: 369550 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0210. Min Act: -0.0005

Data Index: 683666 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0199. Min Act: -0.0005

Data Index: 831998 (C4 (Web Text))

Max Activating Token Index: 962