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

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

Neuron 3590 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: 0.2806. Min Range: -0.2806

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1248005 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2554. Min Act: -0.0000

Data Index: 59272 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2500. Min Act: -0.0000

Data Index: 866449 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1409928 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2428. Min Act: -0.0000

Data Index: 700208 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1613025 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1392830 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2298. Min Act: -0.0000

Data Index: 366169 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1566279 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1174055 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2187. Min Act: -0.0000

Data Index: 564064 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1220215 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1243551 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1919. Min Act: -0.0000

Data Index: 938257 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1929. Min Act: -0.0000

Data Index: 226338 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1255987 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1236949 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1815. Min Act: -0.0000

Data Index: 770764 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1906. Min Act: 0.0001

Data Index: 1652265 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1618920 (Python Code)

Max Activating Token Index: 187