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

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

Neuron 3738 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1098358 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1165176 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5714. Min Act: -0.0000

Data Index: 893564 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5377. Min Act: -0.0000

Data Index: 856486 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5187. Min Act: -0.0000

Data Index: 239926 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5136. Min Act: -0.0000

Data Index: 203361 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5277. Min Act: -0.0001

Data Index: 455993 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5199. Min Act: -0.0000

Data Index: 494453 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.5365. Min Act: -0.0000

Data Index: 375400 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4996. Min Act: 0.0000

Data Index: 110825 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1302888 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4880. Min Act: 0.0000

Data Index: 1192155 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4867. Min Act: -0.0001

Data Index: 1336048 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4691. Min Act: -0.0001

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4580. Min Act: -0.0001

Data Index: 1158716 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4732. Min Act: -0.0000

Data Index: 978399 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4943. Min Act: -0.0001

Data Index: 761231 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4622. Min Act: -0.0000

Data Index: 668629 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4708. Min Act: -0.0000

Data Index: 96213 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.6230. Min Range: -0.6230

Max Act: 0.4590. Min Act: 0.0000

Data Index: 65683 (C4 (Web Text))

Max Activating Token Index: 598