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

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

Neuron 3260 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4129. Min Range: -2.4129

Max Act: 2.4129. Min Act: -0.0000

Data Index: 664596 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 2.4129. Min Range: -2.4129

Max Act: 2.2483. Min Act: -0.0000

Data Index: 1268276 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 2.4129. Min Range: -2.4129

Max Act: 2.1658. Min Act: -0.0000

Data Index: 1028965 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 2.4129. Min Range: -2.4129

Max Act: 2.1354. Min Act: -0.0000

Data Index: 184106 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.9968. Min Act: -0.0000

Data Index: 1029484 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8894. Min Act: -0.0000

Data Index: 1079875 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 2.4129. Min Range: -2.4129

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1114908 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 2.4129. Min Range: -2.4129

Max Act: 2.0400. Min Act: -0.0000

Data Index: 204344 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.9040. Min Act: -0.0000

Data Index: 428944 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8881. Min Act: -0.0000

Data Index: 577125 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8584. Min Act: -0.0000

Data Index: 298689 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.7511. Min Act: -0.0000

Data Index: 942507 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.9492. Min Act: -0.0000

Data Index: 1086249 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.7470. Min Act: -0.0000

Data Index: 555332 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1009356 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8254. Min Act: -0.0000

Data Index: 1359034 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8353. Min Act: -0.0000

Data Index: 628086 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.9181. Min Act: -0.0000

Data Index: 987619 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8100. Min Act: -0.0000

Data Index: 705191 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 2.4129. Min Range: -2.4129

Max Act: 1.8040. Min Act: -0.0000

Data Index: 196855 (C4 (Web Text))

Max Activating Token Index: 718