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

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

Neuron 1389 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: 2.7792. Min Range: -2.7792

Max Act: 2.7792. Min Act: -0.0000

Data Index: 410663 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.5435. Min Act: -0.0000

Data Index: 931705 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.6215. Min Act: -0.0000

Data Index: 705521 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.3454. Min Act: -0.0000

Data Index: 1214044 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.4551. Min Act: -0.0000

Data Index: 886700 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.3121. Min Act: -0.0000

Data Index: 584781 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.2902. Min Act: -0.0000

Data Index: 181394 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.3902. Min Act: -0.0000

Data Index: 18956 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.2046. Min Act: -0.0000

Data Index: 973165 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.2633. Min Act: -0.0000

Data Index: 1240986 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.1210. Min Act: -0.0000

Data Index: 577206 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.2135. Min Act: -0.0000

Data Index: 914980 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.2212. Min Act: -0.0000

Data Index: 1214296 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.0613. Min Act: -0.0000

Data Index: 308326 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.0403. Min Act: -0.0000

Data Index: 315509 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.1759. Min Act: -0.0000

Data Index: 577378 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.0536. Min Act: -0.0000

Data Index: 268081 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.0373. Min Act: -0.0000

Data Index: 1107616 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.1589. Min Act: -0.0000

Data Index: 435656 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 2.7792. Min Range: -2.7792

Max Act: 2.0315. Min Act: -0.0000

Data Index: 1284197 (C4 (Web Text))

Max Activating Token Index: 113