Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1180447 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0443. Min Act: -0.0003

Data Index: 488050 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0403. Min Act: -0.0002

Data Index: 420330 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0416. Min Act: -0.0002

Data Index: 366004 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0392. Min Act: -0.0003

Data Index: 878882 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0398. Min Act: -0.0003

Data Index: 525421 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0004

Data Index: 1214136 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0387. Min Act: -0.0003

Data Index: 631151 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0381. Min Act: -0.0002

Data Index: 371529 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1268878 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1557073 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1100278 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0363. Min Act: -0.0003

Data Index: 434256 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0369. Min Act: -0.0003

Data Index: 368984 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0367. Min Act: -0.0002

Data Index: 432965 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0370. Min Act: -0.0003

Data Index: 576284 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1099968 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1342137 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1283167 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0359. Min Act: -0.0004

Data Index: 301834 (C4 (Web Text))

Max Activating Token Index: 923