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

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

Neuron 1171 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2751. Min Range: -1.2751

Max Act: 1.2751. Min Act: -0.0000

Data Index: 848640 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.8777. Min Act: -0.0000

Data Index: 636893 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.9025. Min Act: -0.0000

Data Index: 640677 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.8407. Min Act: -0.0000

Data Index: 375846 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.8058. Min Act: -0.0000

Data Index: 119333 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7878. Min Act: -0.0000

Data Index: 487025 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7916. Min Act: -0.0000

Data Index: 202011 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7308. Min Act: -0.0000

Data Index: 901260 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1194949 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1063461 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7208. Min Act: -0.0000

Data Index: 416421 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6709. Min Act: -0.0000

Data Index: 300167 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1006418 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.7540. Min Act: -0.0000

Data Index: 304512 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6315. Min Act: -0.0000

Data Index: 977345 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1330516 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1024737 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6474. Min Act: -0.0000

Data Index: 407932 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6300. Min Act: -0.0000

Data Index: 159957 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 1.2751. Min Range: -1.2751

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1189839 (C4 (Web Text))

Max Activating Token Index: 352