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

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

Neuron 58 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: 4.3392. Min Range: -4.3392

Max Act: 4.3392. Min Act: -0.0000

Data Index: 281401 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 4.3392. Min Range: -4.3392

Max Act: 3.7782. Min Act: -0.0000

Data Index: 833969 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 4.3392. Min Range: -4.3392

Max Act: 3.8279. Min Act: -0.0000

Data Index: 828167 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 4.3392. Min Range: -4.3392

Max Act: 3.6612. Min Act: -0.0000

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 4.3392. Min Range: -4.3392

Max Act: 3.5015. Min Act: -0.0000

Data Index: 847680 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 4.3392. Min Range: -4.3392

Max Act: 3.3458. Min Act: -0.0000

Data Index: 1257911 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.9769. Min Act: -0.0000

Data Index: 622387 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 4.3392. Min Range: -4.3392

Max Act: 3.0476. Min Act: -0.0000

Data Index: 1144480 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.7573. Min Act: -0.0000

Data Index: 272019 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.5426. Min Act: -0.0000

Data Index: 786162 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.5884. Min Act: -0.0000

Data Index: 79247 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.5756. Min Act: -0.0000

Data Index: 620704 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.1024. Min Act: -0.0000

Data Index: 426904 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.1718. Min Act: -0.0000

Data Index: 1222219 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.0452. Min Act: -0.0000

Data Index: 1345896 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.1329. Min Act: -0.0000

Data Index: 1198784 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.3744. Min Act: -0.0000

Data Index: 41354 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 4.3392. Min Range: -4.3392

Max Act: 2.0143. Min Act: -0.0000

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 4.3392. Min Range: -4.3392

Max Act: 1.8994. Min Act: -0.0000

Data Index: 389548 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 4.3392. Min Range: -4.3392

Max Act: 1.9674. Min Act: -0.0000

Data Index: 1120643 (C4 (Web Text))

Max Activating Token Index: 977