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

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

Neuron 7 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6459. Min Act: -0.0002

Data Index: 1114286 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.7170. Min Act: -0.0002

Data Index: 575160 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.7127. Min Act: -0.0001

Data Index: 443076 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6880. Min Act: -0.0002

Data Index: 237870 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6417. Min Act: -0.0002

Data Index: 1096958 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.7101. Min Act: -0.0002

Data Index: 266539 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6537. Min Act: -0.0002

Data Index: 15891 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1033931 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6438. Min Act: -0.0002

Data Index: 1009358 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6407. Min Act: -0.0001

Data Index: 78674 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6198. Min Act: -0.0001

Data Index: 327641 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6124. Min Act: -0.0002

Data Index: 1218893 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5728. Min Act: -0.0002

Data Index: 668683 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6273. Min Act: -0.0002

Data Index: 890238 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5508. Min Act: -0.0001

Data Index: 341982 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5768. Min Act: -0.0002

Data Index: 347201 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5300. Min Act: -0.0002

Data Index: 1354657 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5861. Min Act: -0.0001

Data Index: 64401 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5846. Min Act: -0.0001

Data Index: 974901 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5118. Min Act: -0.0002

Data Index: 381389 (C4 (Web Text))

Max Activating Token Index: 778