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

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

Neuron 2193 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.3608. Min Act: -0.0002

Data Index: 890014 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.3017. Min Act: -0.0002

Data Index: 627453 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.3165. Min Act: -0.0002

Data Index: 1310832 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.2540. Min Act: -0.0001

Data Index: 843719 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0876. Min Act: -0.0001

Data Index: 1162336 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1437. Min Act: -0.0002

Data Index: 780773 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1963. Min Act: -0.0001

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0899. Min Act: -0.0002

Data Index: 442419 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0313. Min Act: -0.0001

Data Index: 894617 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0234. Min Act: -0.0001

Data Index: 1305429 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.1711. Min Act: -0.0001

Data Index: 611234 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0100. Min Act: -0.0001

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9421. Min Act: -0.0001

Data Index: 924975 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9905. Min Act: -0.0002

Data Index: 830653 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9569. Min Act: -0.0002

Data Index: 913014 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.8419. Min Act: -0.0001

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 1.3608. Min Range: -1.3608

Max Act: 1.0165. Min Act: -0.0001

Data Index: 187501 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9820. Min Act: -0.0002

Data Index: 1265590 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9009. Min Act: -0.0002

Data Index: 742135 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.3608. Min Range: -1.3608

Max Act: 0.9167. Min Act: -0.0002

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 389