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

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

Neuron 5814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.1379. Min Act: -0.0000

Data Index: 1278342 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 5.4689. Min Range: -5.4689

Max Act: 5.4689. Min Act: -0.0000

Data Index: 884982 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.9845. Min Act: -0.0000

Data Index: 441742 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 5.4689. Min Range: -5.4689

Max Act: 4.1106. Min Act: -0.0000

Data Index: 1154466 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.8830. Min Act: -0.0000

Data Index: 634167 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.1320. Min Act: -0.0000

Data Index: 567820 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.7541. Min Act: -0.0000

Data Index: 1125352 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.4118. Min Act: -0.0000

Data Index: 1205162 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.3787. Min Act: -0.0000

Data Index: 398019 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.8312. Min Act: -0.0000

Data Index: 1035254 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.3934. Min Act: -0.0000

Data Index: 983836 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.3453. Min Act: -0.0000

Data Index: 270461 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.2915. Min Act: -0.0000

Data Index: 28408 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.2246. Min Act: -0.0000

Data Index: 22330 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.3705. Min Act: -0.0000

Data Index: 861786 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.1498. Min Act: -0.0000

Data Index: 637651 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.1169. Min Act: -0.0000

Data Index: 1100941 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.1097. Min Act: -0.0000

Data Index: 751523 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.0970. Min Act: -0.0000

Data Index: 831889 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 5.4689. Min Range: -5.4689

Max Act: 3.0393. Min Act: -0.0000

Data Index: 1265204 (C4 (Web Text))

Max Activating Token Index: 66