Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2756 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.9644. Min Act: -0.0001

Data Index: 170455 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8866. Min Act: -0.0001

Data Index: 170395 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.7447. Min Act: -0.0001

Data Index: 715280 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8511. Min Act: -0.0001

Data Index: 716250 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.7240. Min Act: -0.0001

Data Index: 409071 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.7054. Min Act: -0.0001

Data Index: 1310389 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.8340. Min Act: -0.0001

Data Index: 90828 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6385. Min Act: -0.0001

Data Index: 304206 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6280. Min Act: -0.0001

Data Index: 155586 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6200. Min Act: -0.0001

Data Index: 38255 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.7089. Min Act: -0.0001

Data Index: 848870 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.6191. Min Act: -0.0001

Data Index: 765459 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5907. Min Act: -0.0001

Data Index: 1005925 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5924. Min Act: -0.0001

Data Index: 560129 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5390. Min Act: -0.0001

Data Index: 402064 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5977. Min Act: -0.0001

Data Index: 561429 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5592. Min Act: -0.0001

Data Index: 84128 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.5066. Min Act: -0.0001

Data Index: 889106 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.4770. Min Act: -0.0001

Data Index: 1230018 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.9644. Min Range: -1.9644

Max Act: 1.4604. Min Act: -0.0001

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 1014