Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1670 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1055714 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1468395 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0229. Min Act: -0.0006

Data Index: 617150 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1436954 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0223. Min Act: -0.0006

Data Index: 174040 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1546447 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0205. Min Act: -0.0005

Data Index: 1623069 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1509406 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1501421 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0186. Min Act: -0.0006

Data Index: 116179 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0186. Min Act: -0.0005

Data Index: 1655241 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0184. Min Act: -0.0006

Data Index: 686722 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0183. Min Act: -0.0006

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0179. Min Act: -0.0006

Data Index: 791406 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0174. Min Act: -0.0005

Data Index: 1600410 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0180. Min Act: -0.0006

Data Index: 195853 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0175. Min Act: -0.0005

Data Index: 1500666 (Python Code)

Max Activating Token Index: 903

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0171. Min Act: -0.0005

Data Index: 1550606 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1400325 (Python Code)

Max Activating Token Index: 898

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1610323 (Python Code)

Max Activating Token Index: 697