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

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

Neuron 4038 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1143839 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1239261 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1287288 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2265. Min Act: -0.0001

Data Index: 181417 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2388. Min Act: -0.0001

Data Index: 333224 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2177. Min Act: -0.0001

Data Index: 578299 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2155. Min Act: -0.0001

Data Index: 16201 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2023. Min Act: -0.0001

Data Index: 12397 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1124066 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2051. Min Act: -0.0001

Data Index: 593105 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2069. Min Act: -0.0001

Data Index: 412422 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1969. Min Act: -0.0001

Data Index: 570722 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1184783 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1180450 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1958. Min Act: -0.0001

Data Index: 1302478 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2026. Min Act: -0.0001

Data Index: 432197 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1888. Min Act: -0.0001

Data Index: 366036 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1883. Min Act: -0.0001

Data Index: 167187 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1928. Min Act: -0.0001

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1242615 (C4 (Web Text))

Max Activating Token Index: 7