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

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

Neuron 4400 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0959. Min Range: -2.0959

Max Act: 2.0959. Min Act: -0.0000

Data Index: 2595 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.6103. Min Act: -0.0000

Data Index: 657476 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4213. Min Act: -0.0000

Data Index: 215355 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.5303. Min Act: -0.0000

Data Index: 146862 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.5235. Min Act: -0.0000

Data Index: 219954 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1121542 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1431306 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1192613 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4582. Min Act: -0.0000

Data Index: 326513 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1294636 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4042. Min Act: -0.0000

Data Index: 724846 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1327840 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.3961. Min Act: -0.0000

Data Index: 954481 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.3869. Min Act: -0.0000

Data Index: 825661 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.4217. Min Act: -0.0000

Data Index: 375652 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.3260. Min Act: -0.0000

Data Index: 648000 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1244737 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1170266 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.2753. Min Act: -0.0000

Data Index: 237500 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 2.0959. Min Range: -2.0959

Max Act: 1.2655. Min Act: -0.0000

Data Index: 895870 (C4 (Web Text))

Max Activating Token Index: 956