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

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

Neuron 2860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.3508. Min Act: -0.0001

Data Index: 1128928 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.3204. Min Act: -0.0000

Data Index: 683558 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2916. Min Act: -0.0000

Data Index: 968914 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1094195 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2797. Min Act: -0.0000

Data Index: 733415 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2677. Min Act: -0.0000

Data Index: 206716 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1159492 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2727. Min Act: -0.0000

Data Index: 26934 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2433. Min Act: -0.0000

Data Index: 808084 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2327. Min Act: -0.0000

Data Index: 929957 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2172. Min Act: -0.0001

Data Index: 134907 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2279. Min Act: -0.0000

Data Index: 429516 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1049599 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2201. Min Act: -0.0000

Data Index: 387435 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2169. Min Act: -0.0001

Data Index: 964295 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2147. Min Act: -0.0000

Data Index: 718965 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2124. Min Act: -0.0001

Data Index: 662618 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2094. Min Act: -0.0000

Data Index: 686801 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2078. Min Act: -0.0001

Data Index: 612093 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.3508. Min Range: -0.3508

Max Act: 0.2171. Min Act: -0.0000

Data Index: 225847 (C4 (Web Text))

Max Activating Token Index: 921