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

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

Neuron 1999 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0096. Min Range: -4.0096

Max Act: 4.0096. Min Act: -0.0000

Data Index: 1289159 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 4.0096. Min Range: -4.0096

Max Act: 4.0047. Min Act: -0.0000

Data Index: 677977 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.5935. Min Act: -0.0000

Data Index: 103189 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.6008. Min Act: -0.0000

Data Index: 1341104 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.7760. Min Act: -0.0000

Data Index: 803030 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.5176. Min Act: -0.0000

Data Index: 560909 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.2309. Min Act: -0.0000

Data Index: 846712 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.5265. Min Act: 0.0000

Data Index: 295091 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.2572. Min Act: -0.0000

Data Index: 340731 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.2414. Min Act: 0.0000

Data Index: 145546 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.2127. Min Act: -0.0000

Data Index: 1252379 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3462. Min Act: -0.0000

Data Index: 1137571 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.1690. Min Act: -0.0000

Data Index: 1216835 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.0012. Min Act: -0.0000

Data Index: 282434 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 4.0096. Min Range: -4.0096

Max Act: 2.8577. Min Act: -0.0000

Data Index: 1217014 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 4.0096. Min Range: -4.0096

Max Act: 2.9885. Min Act: -0.0000

Data Index: 1233311 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 4.0096. Min Range: -4.0096

Max Act: 2.9584. Min Act: -0.0000

Data Index: 460394 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 4.0096. Min Range: -4.0096

Max Act: 2.9706. Min Act: -0.0000

Data Index: 972617 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 4.0096. Min Range: -4.0096

Max Act: 2.9626. Min Act: -0.0000

Data Index: 1062660 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 4.0096. Min Range: -4.0096

Max Act: 2.9333. Min Act: -0.0000

Data Index: 23720 (C4 (Web Text))

Max Activating Token Index: 740