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

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

Neuron 421 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: 0.5079. Min Range: -0.5079

Max Act: 0.5079. Min Act: -0.0000

Data Index: 264082 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4095. Min Act: -0.0000

Data Index: 707198 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1179585 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3450. Min Act: -0.0000

Data Index: 609459 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3175. Min Act: -0.0000

Data Index: 918751 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3189. Min Act: -0.0000

Data Index: 349290 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3198. Min Act: -0.0000

Data Index: 481139 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3098. Min Act: -0.0000

Data Index: 16142 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3112. Min Act: -0.0000

Data Index: 838100 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2956. Min Act: -0.0000

Data Index: 369486 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3044. Min Act: -0.0000

Data Index: 241937 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2899. Min Act: -0.0000

Data Index: 13226 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2727. Min Act: -0.0000

Data Index: 68474 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2682. Min Act: -0.0000

Data Index: 417540 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2439. Min Act: -0.0000

Data Index: 650197 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1128153 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2698. Min Act: -0.0000

Data Index: 894223 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2678. Min Act: -0.0000

Data Index: 359154 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2681. Min Act: -0.0000

Data Index: 729983 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.2764. Min Act: -0.0000

Data Index: 523672 (C4 (Web Text))

Max Activating Token Index: 569