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

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

Neuron 4396 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1903. Min Act: -0.0001

Data Index: 1540910 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1360096 (Python Code)

Max Activating Token Index: 109

Text #2

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1638786 (Python Code)

Max Activating Token Index: 444

Text #3

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1369. Min Act: -0.0001

Data Index: 169394 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1632289 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1051708 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1477947 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1241. Min Act: -0.0001

Data Index: 704026 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1237. Min Act: -0.0001

Data Index: 404107 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1306. Min Act: -0.0001

Data Index: 989515 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1627709 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1059126 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1633774 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1263720 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1104331 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1133. Min Act: -0.0001

Data Index: 743379 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1254067 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1097. Min Act: -0.0001

Data Index: 347361 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1154. Min Act: -0.0001

Data Index: 155493 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.1903. Min Range: -0.1903

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1278349 (C4 (Web Text))

Max Activating Token Index: 906