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

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

Neuron 1764 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9348. Min Act: 0.0000

Data Index: 861679 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7856. Min Act: -0.0000

Data Index: 154365 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1402143 (Python Code)

Max Activating Token Index: 951

Text #3

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6709. Min Act: -0.0000

Data Index: 672815 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1548199 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1551657 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1094697 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1328309 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5868. Min Act: -0.0000

Data Index: 515754 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1259957 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5740. Min Act: 0.0000

Data Index: 716046 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1129247 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1095068 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1628975 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5833. Min Act: -0.0000

Data Index: 963565 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1373188 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5516. Min Act: -0.0000

Data Index: 886159 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1468067 (Python Code)

Max Activating Token Index: 213

Text #18

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1337741 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.5048. Min Act: -0.0000

Data Index: 732591 (C4 (Web Text))

Max Activating Token Index: 498