Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1195 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.6187. Min Act: -0.0001

Data Index: 708617 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.4942. Min Act: -0.0001

Data Index: 1285703 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.4155. Min Act: -0.0001

Data Index: 1011448 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.4102. Min Act: -0.0001

Data Index: 927888 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.4047. Min Act: -0.0001

Data Index: 122383 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.3338. Min Act: -0.0001

Data Index: 253918 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.3007. Min Act: -0.0001

Data Index: 1255554 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2903. Min Act: -0.0001

Data Index: 1173393 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.3034. Min Act: -0.0001

Data Index: 502059 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2575. Min Act: -0.0001

Data Index: 599529 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2480. Min Act: -0.0001

Data Index: 1190764 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2480. Min Act: -0.0001

Data Index: 195687 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2480. Min Act: -0.0001

Data Index: 344914 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2074. Min Act: -0.0001

Data Index: 984751 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2234. Min Act: -0.0001

Data Index: 273159 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2946. Min Act: -0.0001

Data Index: 1104908 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2440. Min Act: -0.0001

Data Index: 324153 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2345. Min Act: -0.0001

Data Index: 639596 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.2171. Min Act: -0.0001

Data Index: 746355 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.6187. Min Range: -1.6187

Max Act: 1.1388. Min Act: -0.0001

Data Index: 319511 (C4 (Web Text))

Max Activating Token Index: 676