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

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

Neuron 2239 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.5213. Min Act: -0.0000

Data Index: 193803 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1081107 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.2836. Min Act: -0.0000

Data Index: 330978 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.2100. Min Act: -0.0000

Data Index: 569816 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.2298. Min Act: -0.0000

Data Index: 137702 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.1215. Min Act: -0.0000

Data Index: 649324 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.1565. Min Act: -0.0000

Data Index: 778862 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.5213. Min Range: -1.5213

Max Act: 1.0729. Min Act: -0.0000

Data Index: 363111 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.9141. Min Act: -0.0001

Data Index: 1647305 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1418037 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1084400 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1625332 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1423849 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1381142 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1541260 (Python Code)

Max Activating Token Index: 271

Text #15

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1650308 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1366997 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1022901 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1581087 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 1.5213. Min Range: -1.5213

Max Act: 0.8907. Min Act: -0.0000

Data Index: 497928 (C4 (Web Text))

Max Activating Token Index: 950