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

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

Neuron 3708 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.8875. Min Act: -0.0001

Data Index: 354905 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.5005. Min Act: -0.0000

Data Index: 531297 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3773. Min Act: -0.0000

Data Index: 105702 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.4103. Min Act: -0.0001

Data Index: 149675 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3503. Min Act: -0.0001

Data Index: 770057 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.3672. Min Act: -0.0001

Data Index: 1033296 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1345. Min Act: -0.0001

Data Index: 364941 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1714. Min Act: -0.0000

Data Index: 910508 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1041. Min Act: -0.0000

Data Index: 632668 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1106. Min Act: -0.0000

Data Index: 828083 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.1165. Min Act: -0.0000

Data Index: 887753 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.0341. Min Act: -0.0000

Data Index: 899116 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.0007. Min Act: -0.0000

Data Index: 775075 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 1.8875. Min Range: -1.8875

Max Act: 1.0255. Min Act: -0.0000

Data Index: 975446 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 1.8875. Min Range: -1.8875

Max Act: 0.9759. Min Act: -0.0001

Data Index: 268881 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.8875. Min Range: -1.8875

Max Act: 0.9480. Min Act: -0.0000

Data Index: 25926 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.8875. Min Range: -1.8875

Max Act: 0.9419. Min Act: -0.0000

Data Index: 198965 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.8875. Min Range: -1.8875

Max Act: 0.8897. Min Act: -0.0001

Data Index: 641975 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.8875. Min Range: -1.8875

Max Act: 0.9122. Min Act: -0.0001

Data Index: 840650 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 1.8875. Min Range: -1.8875

Max Act: 0.9148. Min Act: -0.0001

Data Index: 825022 (C4 (Web Text))

Max Activating Token Index: 970