Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3241 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1070485 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1531. Min Act: -0.0000

Data Index: 117725 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1528. Min Act: -0.0001

Data Index: 575911 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1181525 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1340996 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1232. Min Act: -0.0001

Data Index: 1103406 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1111. Min Act: -0.0001

Data Index: 742685 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1224. Min Act: -0.0001

Data Index: 174365 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1131. Min Act: -0.0001

Data Index: 557604 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1293126 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.0987. Min Act: -0.0001

Data Index: 179074 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1251. Min Act: -0.0001

Data Index: 929071 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1163145 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1183. Min Act: -0.0001

Data Index: 546145 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1049. Min Act: -0.0001

Data Index: 254336 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1128. Min Act: -0.0001

Data Index: 915866 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1106. Min Act: -0.0001

Data Index: 936067 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1105. Min Act: -0.0001

Data Index: 651339 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1075. Min Act: -0.0001

Data Index: 270230 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1109. Min Act: -0.0001

Data Index: 424368 (C4 (Web Text))

Max Activating Token Index: 74