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

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

Neuron 2320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.9092. Min Act: -0.0000

Data Index: 272062 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.8537. Min Act: -0.0000

Data Index: 1129929 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.5379. Min Act: -0.0000

Data Index: 201613 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.2272. Min Act: -0.0000

Data Index: 582180 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.2810. Min Act: -0.0000

Data Index: 624043 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.1434. Min Act: -0.0000

Data Index: 1636223 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.2222. Min Act: -0.0000

Data Index: 368770 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.2165. Min Act: -0.0000

Data Index: 805314 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1606380 (Python Code)

Max Activating Token Index: 886

Text #9

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.1616. Min Act: -0.0000

Data Index: 1647810 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.1641. Min Act: -0.0000

Data Index: 120901 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.2743. Min Act: -0.0000

Data Index: 1270092 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.2235. Min Act: -0.0000

Data Index: 921423 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.0907. Min Act: -0.0000

Data Index: 1577674 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1579955 (Python Code)

Max Activating Token Index: 337

Text #15

Max Range: 2.9092. Min Range: -2.9092

Max Act: 1.8243. Min Act: -0.0000

Data Index: 1503983 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 2.9092. Min Range: -2.9092

Max Act: 2.0127. Min Act: -0.0000

Data Index: 1608919 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 2.9092. Min Range: -2.9092

Max Act: 1.9035. Min Act: -0.0000

Data Index: 1071844 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 2.9092. Min Range: -2.9092

Max Act: 1.9946. Min Act: -0.0000

Data Index: 1433074 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 2.9092. Min Range: -2.9092

Max Act: 1.8830. Min Act: -0.0000

Data Index: 806665 (C4 (Web Text))

Max Activating Token Index: 784