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

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

Neuron 1386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.9873. Min Range: -8.9873

Max Act: 8.9873. Min Act: -0.0000

Data Index: 1180823 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 8.9873. Min Range: -8.9873

Max Act: 8.3132. Min Act: -0.0000

Data Index: 1203440 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 8.9873. Min Range: -8.9873

Max Act: 7.9120. Min Act: -0.0000

Data Index: 1710 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 8.9873. Min Range: -8.9873

Max Act: 7.8919. Min Act: -0.0000

Data Index: 1343040 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 8.9873. Min Range: -8.9873

Max Act: 7.3684. Min Act: -0.0000

Data Index: 1236208 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 8.9873. Min Range: -8.9873

Max Act: 7.5269. Min Act: -0.0000

Data Index: 807406 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 8.9873. Min Range: -8.9873

Max Act: 7.4375. Min Act: -0.0000

Data Index: 1354927 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.9737. Min Act: -0.0000

Data Index: 1015347 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.7855. Min Act: -0.0000

Data Index: 648058 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.5872. Min Act: -0.0000

Data Index: 601672 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.5178. Min Act: -0.0000

Data Index: 124198 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.6501. Min Act: -0.0000

Data Index: 1188776 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.6352. Min Act: -0.0000

Data Index: 428771 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.6316. Min Act: -0.0000

Data Index: 1331649 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.6250. Min Act: -0.0000

Data Index: 69737 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.4065. Min Act: -0.0000

Data Index: 330364 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.5465. Min Act: -0.0000

Data Index: 201782 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 8.9873. Min Range: -8.9873

Max Act: 5.8926. Min Act: -0.0000

Data Index: 211614 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.0799. Min Act: -0.0000

Data Index: 1308621 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 8.9873. Min Range: -8.9873

Max Act: 6.2665. Min Act: -0.0000

Data Index: 1331188 (C4 (Web Text))

Max Activating Token Index: 680