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

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

Neuron 1655 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: 0.2392. Min Range: -0.2392

Max Act: 0.2392. Min Act: -0.0001

Data Index: 360133 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1132513 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1160480 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2258. Min Act: -0.0000

Data Index: 105492 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2242. Min Act: -0.0001

Data Index: 842730 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2116. Min Act: -0.0000

Data Index: 631183 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2001. Min Act: -0.0000

Data Index: 607718 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1058901 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2126. Min Act: -0.0000

Data Index: 427256 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2074. Min Act: -0.0000

Data Index: 553040 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2172. Min Act: -0.0001

Data Index: 114223 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2076. Min Act: -0.0000

Data Index: 639056 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2071. Min Act: -0.0001

Data Index: 571417 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1964. Min Act: -0.0001

Data Index: 331945 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1937. Min Act: -0.0000

Data Index: 952478 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1974. Min Act: -0.0000

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1943. Min Act: -0.0001

Data Index: 598088 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1937. Min Act: -0.0000

Data Index: 817789 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1243590 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.2392. Min Range: -0.2392

Max Act: 0.1795. Min Act: -0.0000

Data Index: 888212 (C4 (Web Text))

Max Activating Token Index: 904