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

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

Neuron 5925 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.4031. Min Act: -0.0000

Data Index: 1119572 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.0846. Min Act: -0.0000

Data Index: 466854 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.9955. Min Act: -0.0000

Data Index: 805650 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.9037. Min Act: -0.0000

Data Index: 702014 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.8303. Min Act: -0.0000

Data Index: 1203736 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.6402. Min Act: -0.0000

Data Index: 928381 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.6047. Min Act: -0.0000

Data Index: 507563 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5986. Min Act: -0.0000

Data Index: 1597649 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5571. Min Act: -0.0000

Data Index: 1417162 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5295. Min Act: -0.0000

Data Index: 1019712 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5328. Min Act: -0.0000

Data Index: 616968 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5128. Min Act: -0.0000

Data Index: 1161542 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.4823. Min Act: -0.0000

Data Index: 262165 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5077. Min Act: -0.0000

Data Index: 218554 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.2520. Min Act: -0.0000

Data Index: 89108 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5011. Min Act: -0.0000

Data Index: 697808 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.2757. Min Act: -0.0000

Data Index: 661217 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.3944. Min Act: -0.0000

Data Index: 607140 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.5097. Min Act: -0.0000

Data Index: 912101 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 3.4031. Min Range: -3.4031

Max Act: 2.4803. Min Act: -0.0000

Data Index: 216806 (C4 (Web Text))

Max Activating Token Index: 987