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

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

Neuron 1603 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: 2.2376. Min Range: -2.2376

Max Act: 2.2376. Min Act: -0.0000

Data Index: 355654 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 2.2376. Min Range: -2.2376

Max Act: 2.2154. Min Act: -0.0000

Data Index: 164653 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 2.2376. Min Range: -2.2376

Max Act: 2.0733. Min Act: -0.0000

Data Index: 114563 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.7856. Min Act: -0.0000

Data Index: 142023 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1297120 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.6364. Min Act: -0.0000

Data Index: 904768 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5389. Min Act: -0.0000

Data Index: 1335959 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.6276. Min Act: -0.0000

Data Index: 1008774 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.4915. Min Act: -0.0000

Data Index: 409456 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5662. Min Act: -0.0000

Data Index: 263962 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5363. Min Act: -0.0000

Data Index: 1263267 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5084. Min Act: -0.0000

Data Index: 1133449 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5801. Min Act: -0.0000

Data Index: 343266 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5959. Min Act: -0.0000

Data Index: 36174 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1277017 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.4823. Min Act: -0.0000

Data Index: 63547 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1196095 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5091. Min Act: -0.0000

Data Index: 1060860 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.5030. Min Act: -0.0000

Data Index: 85115 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.2376. Min Range: -2.2376

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1351083 (C4 (Web Text))

Max Activating Token Index: 1014