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

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

Neuron 400 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: 4.0554. Min Range: -4.0554

Max Act: 3.9990. Min Act: -0.0000

Data Index: 377476 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 4.0554. Min Range: -4.0554

Max Act: 4.0554. Min Act: -0.0000

Data Index: 963909 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.9750. Min Act: -0.0000

Data Index: 3431 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 4.0554. Min Range: -4.0554

Max Act: 4.0511. Min Act: -0.0000

Data Index: 1299230 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.8632. Min Act: -0.0000

Data Index: 499766 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 4.0554. Min Range: -4.0554

Max Act: 4.0132. Min Act: -0.0000

Data Index: 14120 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.8240. Min Act: -0.0000

Data Index: 95406 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.7267. Min Act: -0.0000

Data Index: 44564 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.7082. Min Act: -0.0000

Data Index: 1317542 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.8738. Min Act: -0.0000

Data Index: 743109 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 4.0554. Min Range: -4.0554

Max Act: 4.0211. Min Act: -0.0000

Data Index: 990499 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.7150. Min Act: -0.0000

Data Index: 1261615 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.7085. Min Act: -0.0000

Data Index: 698636 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.8595. Min Act: -0.0000

Data Index: 1224122 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.3850. Min Act: -0.0000

Data Index: 707591 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.4822. Min Act: -0.0000

Data Index: 1091203 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.4494. Min Act: -0.0000

Data Index: 96100 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.4191. Min Act: -0.0000

Data Index: 1214079 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.5887. Min Act: -0.0000

Data Index: 765226 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 4.0554. Min Range: -4.0554

Max Act: 3.2788. Min Act: -0.0000

Data Index: 35856 (C4 (Web Text))

Max Activating Token Index: 997