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

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

Neuron 5577 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: 2.8282. Min Range: -2.8282

Max Act: 2.8282. Min Act: -0.0000

Data Index: 729752 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.5644. Min Act: -0.0000

Data Index: 13623 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.5553. Min Act: -0.0000

Data Index: 855972 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.4736. Min Act: -0.0000

Data Index: 325195 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.3201. Min Act: -0.0000

Data Index: 95774 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.2852. Min Act: -0.0000

Data Index: 248938 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.2656. Min Act: -0.0000

Data Index: 39400 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.3304. Min Act: -0.0000

Data Index: 935252 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.0416. Min Act: -0.0000

Data Index: 1004082 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.1621. Min Act: -0.0000

Data Index: 1160284 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.1435. Min Act: -0.0000

Data Index: 1326645 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.9734. Min Act: -0.0000

Data Index: 1304086 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.0953. Min Act: -0.0000

Data Index: 153874 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.9811. Min Act: -0.0000

Data Index: 847663 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.8352. Min Act: -0.0000

Data Index: 341300 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.8262. Min Act: -0.0000

Data Index: 1253020 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.9358. Min Act: -0.0000

Data Index: 306889 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.9024. Min Act: -0.0000

Data Index: 882478 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 2.8282. Min Range: -2.8282

Max Act: 1.8912. Min Act: -0.0000

Data Index: 1439388 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 2.8282. Min Range: -2.8282

Max Act: 2.1128. Min Act: -0.0000

Data Index: 1038471 (C4 (Web Text))

Max Activating Token Index: 940