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

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

Neuron 1505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2967. Min Act: -0.0000

Data Index: 1143025 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2864. Min Act: -0.0000

Data Index: 567302 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1234250 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1689. Min Act: -0.0000

Data Index: 194725 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1166363 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1041597 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.2098. Min Act: -0.0000

Data Index: 961161 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1185. Min Act: -0.0000

Data Index: 479095 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1102. Min Act: -0.0000

Data Index: 897369 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1006000 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1776. Min Act: -0.0000

Data Index: 423908 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0461. Min Act: -0.0000

Data Index: 701666 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1259956 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0426. Min Act: -0.0000

Data Index: 862983 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0390. Min Act: -0.0000

Data Index: 309446 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1243852 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9975. Min Act: -0.0000

Data Index: 690767 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0612. Min Act: -0.0000

Data Index: 180074 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.3472. Min Range: -1.3472

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1308198 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.3472. Min Range: -1.3472

Max Act: 0.9835. Min Act: -0.0000

Data Index: 53845 (C4 (Web Text))

Max Activating Token Index: 357