Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0000

Data Index: 981183 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1110. Min Act: -0.0000

Data Index: 613922 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1311106 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1026. Min Act: -0.0001

Data Index: 373739 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0988. Min Act: -0.0000

Data Index: 877904 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1178062 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1000753 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0867. Min Act: -0.0000

Data Index: 253726 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1243938 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0909. Min Act: -0.0000

Data Index: 932329 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1321205 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0866. Min Act: -0.0000

Data Index: 775316 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0866. Min Act: -0.0001

Data Index: 945640 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0784. Min Act: -0.0000

Data Index: 462620 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0794. Min Act: -0.0001

Data Index: 301732 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1186287 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0770. Min Act: -0.0001

Data Index: 656677 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1244118 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1302499 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0742. Min Act: -0.0000

Data Index: 390541 (C4 (Web Text))

Max Activating Token Index: 258