Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3362 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2416. Min Range: -1.2416

Max Act: 1.1715. Min Act: -0.0000

Data Index: 776239 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.2416. Min Range: -1.2416

Max Act: 1.1822. Min Act: -0.0000

Data Index: 781059 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.2416. Min Range: -1.2416

Max Act: 1.2109. Min Act: -0.0000

Data Index: 580204 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.2416. Min Range: -1.2416

Max Act: 1.2416. Min Act: -0.0000

Data Index: 954684 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.2416. Min Range: -1.2416

Max Act: 1.0817. Min Act: -0.0000

Data Index: 357809 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 1.2416. Min Range: -1.2416

Max Act: 1.0786. Min Act: -0.0000

Data Index: 369295 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.9280. Min Act: -0.0001

Data Index: 863510 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.9765. Min Act: -0.0000

Data Index: 240419 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.9138. Min Act: -0.0001

Data Index: 1430064 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.9180. Min Act: -0.0000

Data Index: 33195 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.9350. Min Act: -0.0000

Data Index: 16569 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8571. Min Act: -0.0000

Data Index: 14976 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.9749. Min Act: -0.0000

Data Index: 841612 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1108038 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8749. Min Act: -0.0000

Data Index: 546069 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1115125 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8326. Min Act: -0.0000

Data Index: 51288 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1179368 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8858. Min Act: -0.0001

Data Index: 155599 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.2416. Min Range: -1.2416

Max Act: 0.8561. Min Act: -0.0000

Data Index: 400658 (C4 (Web Text))

Max Activating Token Index: 464