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

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

Neuron 3337 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: 2.4495. Min Range: -2.4495

Max Act: 2.4495. Min Act: -0.0000

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.4235. Min Act: -0.0000

Data Index: 1331866 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1530337 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.3841. Min Act: -0.0000

Data Index: 1319162 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0422. Min Act: -0.0000

Data Index: 452590 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0676. Min Act: -0.0000

Data Index: 1137313 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.1868. Min Act: -0.0000

Data Index: 637109 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0628. Min Act: -0.0000

Data Index: 919026 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.1151. Min Act: -0.0000

Data Index: 817391 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.4495. Min Range: -2.4495

Max Act: 2.0520. Min Act: -0.0000

Data Index: 761740 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.9350. Min Act: -0.0000

Data Index: 1357575 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6422. Min Act: -0.0000

Data Index: 977805 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6827. Min Act: -0.0000

Data Index: 131691 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6330. Min Act: -0.0000

Data Index: 1455456 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.5999. Min Act: -0.0000

Data Index: 630047 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6778. Min Act: -0.0000

Data Index: 205958 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1029353 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1171231 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.6502. Min Act: -0.0000

Data Index: 1271081 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 2.4495. Min Range: -2.4495

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1037446 (C4 (Web Text))

Max Activating Token Index: 722