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

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

Neuron 1628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.9596. Min Act: -0.0001

Data Index: 202783 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.2097. Min Act: -0.0000

Data Index: 545150 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.2156. Min Act: -0.0001

Data Index: 194737 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1304. Min Act: -0.0001

Data Index: 1236432 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1246. Min Act: -0.0001

Data Index: 1350219 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1549. Min Act: -0.0001

Data Index: 423250 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1281. Min Act: -0.0001

Data Index: 867780 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1507. Min Act: -0.0001

Data Index: 1169171 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1086. Min Act: -0.0001

Data Index: 25532 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.1106. Min Act: -0.0001

Data Index: 548475 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9969. Min Act: -0.0001

Data Index: 548045 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9964. Min Act: -0.0000

Data Index: 840510 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9821. Min Act: -0.0001

Data Index: 1115088 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1011511 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9795. Min Act: -0.0001

Data Index: 421793 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.9596. Min Range: -1.9596

Max Act: 1.0069. Min Act: -0.0001

Data Index: 919066 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9926. Min Act: -0.0001

Data Index: 558701 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9579. Min Act: -0.0001

Data Index: 7631 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9546. Min Act: -0.0001

Data Index: 411950 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.9596. Min Range: -1.9596

Max Act: 0.9413. Min Act: -0.0000

Data Index: 468618 (C4 (Web Text))

Max Activating Token Index: 306