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

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

Neuron 3369 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1146643 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2504. Min Act: -0.0000

Data Index: 693842 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2488. Min Act: -0.0000

Data Index: 116693 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2442. Min Act: -0.0000

Data Index: 50620 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2360. Min Act: -0.0000

Data Index: 216180 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2386. Min Act: -0.0000

Data Index: 904561 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2296. Min Act: -0.0000

Data Index: 58843 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2307. Min Act: 0.0000

Data Index: 743608 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2237. Min Act: 0.0000

Data Index: 814839 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2179. Min Act: -0.0000

Data Index: 426388 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2081. Min Act: -0.0000

Data Index: 85533 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2143. Min Act: -0.0000

Data Index: 890460 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1238866 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2044. Min Act: -0.0000

Data Index: 69183 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2021. Min Act: -0.0000

Data Index: 460430 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1058274 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1043395 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1216709 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1780. Min Act: -0.0001

Data Index: 318918 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1836. Min Act: -0.0000

Data Index: 496413 (C4 (Web Text))

Max Activating Token Index: 778