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

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

Neuron 5057 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: 2.8963. Min Range: -2.8963

Max Act: 2.8963. Min Act: 0.0001

Data Index: 1072527 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.8448. Min Act: -0.0000

Data Index: 166922 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.2826. Min Act: -0.0000

Data Index: 1461365 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.2807. Min Act: 0.0000

Data Index: 358567 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.0291. Min Act: -0.0000

Data Index: 694897 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.0823. Min Act: 0.0000

Data Index: 1656794 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.9775. Min Act: -0.0000

Data Index: 1504377 (Python Code)

Max Activating Token Index: 452

Text #7

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.9048. Min Act: 0.0000

Data Index: 1372553 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1116114 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1558172 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 2.8963. Min Range: -2.8963

Max Act: 2.0061. Min Act: 0.0002

Data Index: 1543969 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.7803. Min Act: 0.0000

Data Index: 1594252 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.8215. Min Act: -0.0000

Data Index: 733026 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.6175. Min Act: 0.0000

Data Index: 1584325 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.8246. Min Act: 0.0000

Data Index: 651791 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1513281 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.6953. Min Act: -0.0000

Data Index: 1562289 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.8628. Min Act: 0.0000

Data Index: 410099 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1014188 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 2.8963. Min Range: -2.8963

Max Act: 1.8315. Min Act: -0.0000

Data Index: 1555394 (Python Code)

Max Activating Token Index: 438