Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 486 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1015517 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1302726 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2256. Min Act: -0.0001

Data Index: 206457 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2193. Min Act: -0.0001

Data Index: 23937 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2183. Min Act: -0.0000

Data Index: 434508 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2181. Min Act: -0.0001

Data Index: 565002 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2082. Min Act: -0.0001

Data Index: 986262 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2051. Min Act: -0.0001

Data Index: 320188 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2091. Min Act: -0.0001

Data Index: 510839 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1013258 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1112343 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2054. Min Act: -0.0001

Data Index: 371099 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2093. Min Act: -0.0001

Data Index: 679002 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1955. Min Act: -0.0001

Data Index: 575224 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1070346 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1631532 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1912. Min Act: -0.0001

Data Index: 160199 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2033. Min Act: -0.0001

Data Index: 706359 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1953. Min Act: -0.0001

Data Index: 533591 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1113351 (C4 (Web Text))

Max Activating Token Index: 162