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

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

Neuron 4855 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4254. Min Act: -0.0001

Data Index: 1374673 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4478. Min Act: -0.0001

Data Index: 1412380 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4789. Min Act: -0.0001

Data Index: 461885 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4830. Min Act: -0.0000

Data Index: 1451959 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1705. Min Act: -0.0001

Data Index: 1627828 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.4243. Min Act: -0.0001

Data Index: 1492640 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3140. Min Act: -0.0001

Data Index: 1644581 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3549. Min Act: -0.0001

Data Index: 1368647 (Python Code)

Max Activating Token Index: 761

Text #8

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2381. Min Act: -0.0001

Data Index: 462771 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1406027 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2346. Min Act: -0.0001

Data Index: 1364824 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1437937 (Python Code)

Max Activating Token Index: 166

Text #12

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2683. Min Act: -0.0001

Data Index: 1607703 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2610. Min Act: -0.0001

Data Index: 1405382 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2191. Min Act: -0.0001

Data Index: 1447461 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2106. Min Act: -0.0001

Data Index: 1639450 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.1116. Min Act: -0.0001

Data Index: 1494007 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2740. Min Act: -0.0001

Data Index: 1507307 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.0758. Min Act: -0.0001

Data Index: 1367729 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.2049. Min Act: -0.0001

Data Index: 1545594 (Python Code)

Max Activating Token Index: 56