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

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

Neuron 3641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3257. Min Act: -0.0001

Data Index: 605997 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2463. Min Act: -0.0001

Data Index: 1059909 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2930. Min Act: -0.0001

Data Index: 1300839 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1843. Min Act: -0.0001

Data Index: 772903 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0378. Min Act: -0.0001

Data Index: 512370 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0455. Min Act: -0.0001

Data Index: 1120390 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9871. Min Act: -0.0001

Data Index: 374284 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9773. Min Act: -0.0001

Data Index: 445634 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1168. Min Act: -0.0001

Data Index: 748173 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0112. Min Act: -0.0001

Data Index: 913540 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9431. Min Act: -0.0001

Data Index: 118116 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9454. Min Act: -0.0001

Data Index: 634506 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0294. Min Act: -0.0001

Data Index: 180477 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9488. Min Act: -0.0001

Data Index: 590873 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1334223 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9353. Min Act: -0.0001

Data Index: 904346 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.8882. Min Act: -0.0001

Data Index: 265381 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9327. Min Act: -0.0001

Data Index: 430865 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.8490. Min Act: -0.0001

Data Index: 794618 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.8710. Min Act: -0.0001

Data Index: 158370 (C4 (Web Text))

Max Activating Token Index: 963