Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 926 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1351. Min Act: -0.0003

Data Index: 1189147 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0003

Data Index: 1154015 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1277. Min Act: -0.0003

Data Index: 946474 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1347. Min Act: -0.0003

Data Index: 610181 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1217. Min Act: -0.0003

Data Index: 761950 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1175. Min Act: -0.0003

Data Index: 697214 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1228. Min Act: -0.0003

Data Index: 1072841 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1149. Min Act: -0.0003

Data Index: 447209 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1130. Min Act: -0.0003

Data Index: 501109 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1086. Min Act: -0.0003

Data Index: 925081 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1201888 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1042. Min Act: -0.0003

Data Index: 238393 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1108. Min Act: -0.0003

Data Index: 319880 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1149. Min Act: -0.0003

Data Index: 847600 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1086. Min Act: -0.0003

Data Index: 17033 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1183. Min Act: -0.0003

Data Index: 757852 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1054. Min Act: -0.0003

Data Index: 262180 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1022. Min Act: -0.0003

Data Index: 1273183 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1157. Min Act: -0.0003

Data Index: 1302189 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1043. Min Act: -0.0003

Data Index: 1307099 (C4 (Web Text))

Max Activating Token Index: 947