Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 346 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.3172. Min Act: -0.0001

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2691. Min Act: -0.0000

Data Index: 945402 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2453. Min Act: -0.0000

Data Index: 939455 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1167146 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2163. Min Act: -0.0000

Data Index: 691072 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1133892 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2104. Min Act: -0.0000

Data Index: 664040 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1284412 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1918. Min Act: -0.0001

Data Index: 603981 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2105. Min Act: -0.0001

Data Index: 912958 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1681. Min Act: -0.0000

Data Index: 42878 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1946. Min Act: -0.0000

Data Index: 714008 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1810. Min Act: -0.0001

Data Index: 355789 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1846. Min Act: -0.0001

Data Index: 891709 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1757. Min Act: -0.0001

Data Index: 245166 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1710. Min Act: -0.0001

Data Index: 366373 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1778. Min Act: -0.0000

Data Index: 619614 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1904. Min Act: -0.0001

Data Index: 789091 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1046900 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.1872. Min Act: -0.0000

Data Index: 418707 (C4 (Web Text))

Max Activating Token Index: 775