Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3378 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.6705. Min Act: -0.0001

Data Index: 731481 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.3665. Min Act: -0.0001

Data Index: 434912 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1192928 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.1142. Min Act: -0.0001

Data Index: 1016774 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.1377. Min Act: -0.0001

Data Index: 797666 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.0744. Min Act: -0.0000

Data Index: 158940 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.0412. Min Act: -0.0001

Data Index: 549654 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.9532. Min Act: -0.0001

Data Index: 1196552 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.9550. Min Act: -0.0001

Data Index: 897387 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1320221 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.6705. Min Range: -1.6705

Max Act: 1.0052. Min Act: -0.0001

Data Index: 475853 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.8615. Min Act: -0.0001

Data Index: 604930 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.8941. Min Act: -0.0001

Data Index: 994958 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.8006. Min Act: -0.0001

Data Index: 96740 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.8750. Min Act: -0.0001

Data Index: 979288 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1095561 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.7804. Min Act: -0.0001

Data Index: 813828 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.7807. Min Act: -0.0000

Data Index: 248044 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.7987. Min Act: -0.0001

Data Index: 272358 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 1.6705. Min Range: -1.6705

Max Act: 0.7345. Min Act: -0.0001

Data Index: 996134 (C4 (Web Text))

Max Activating Token Index: 270