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

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

Neuron 4550 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1122. Min Range: -2.1122

Max Act: 2.1122. Min Act: -0.0000

Data Index: 1309359 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.8400. Min Act: -0.0000

Data Index: 81907 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1152951 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1265413 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.6568. Min Act: -0.0000

Data Index: 834452 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.7134. Min Act: -0.0000

Data Index: 865385 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.6038. Min Act: -0.0000

Data Index: 491180 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1216640 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.6420. Min Act: -0.0001

Data Index: 1261913 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.5075. Min Act: -0.0000

Data Index: 500661 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.3369. Min Act: -0.0000

Data Index: 628861 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.4077. Min Act: -0.0000

Data Index: 69888 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.4782. Min Act: -0.0000

Data Index: 471534 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.4725. Min Act: -0.0000

Data Index: 324875 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.3934. Min Act: -0.0000

Data Index: 697295 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.3180. Min Act: -0.0000

Data Index: 50123 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1060916 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.3438. Min Act: -0.0000

Data Index: 356447 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.4842. Min Act: -0.0000

Data Index: 622368 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 2.1122. Min Range: -2.1122

Max Act: 1.4833. Min Act: -0.0000

Data Index: 83235 (C4 (Web Text))

Max Activating Token Index: 317