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

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

Neuron 4253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2929. Min Act: -0.0000

Data Index: 75331 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2456. Min Act: -0.0000

Data Index: 397088 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2378. Min Act: -0.0000

Data Index: 28643 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2140. Min Act: -0.0000

Data Index: 50668 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2134. Min Act: -0.0000

Data Index: 539800 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.2143. Min Act: -0.0000

Data Index: 707045 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1908. Min Act: -0.0000

Data Index: 523253 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1774. Min Act: -0.0000

Data Index: 181875 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1672. Min Act: -0.0000

Data Index: 30973 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1598. Min Act: -0.0000

Data Index: 959597 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1401. Min Act: -0.0000

Data Index: 995249 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1376. Min Act: -0.0000

Data Index: 242103 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1465. Min Act: -0.0000

Data Index: 631594 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1238433 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1287. Min Act: -0.0000

Data Index: 499232 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1333. Min Act: -0.0000

Data Index: 778682 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1304. Min Act: -0.0000

Data Index: 926184 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1326. Min Act: -0.0000

Data Index: 219713 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1191. Min Act: -0.0000

Data Index: 851240 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.2929. Min Range: -0.2929

Max Act: 0.1079. Min Act: -0.0000

Data Index: 354526 (C4 (Web Text))

Max Activating Token Index: 392