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

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

Neuron 2753 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: 1.7320. Min Range: -1.7320

Max Act: 1.7045. Min Act: -0.0000

Data Index: 92451 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.7320. Min Act: -0.0001

Data Index: 473699 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.6248. Min Act: -0.0000

Data Index: 1057504 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1309171 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.4721. Min Act: -0.0000

Data Index: 868996 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.5077. Min Act: -0.0001

Data Index: 1304802 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3914. Min Act: -0.0001

Data Index: 484852 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3854. Min Act: -0.0001

Data Index: 84072 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3714. Min Act: -0.0000

Data Index: 750162 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3116. Min Act: -0.0000

Data Index: 88788 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3313. Min Act: -0.0000

Data Index: 11278 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.2877. Min Act: -0.0001

Data Index: 414709 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3223. Min Act: -0.0001

Data Index: 1155402 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3618. Min Act: -0.0001

Data Index: 610217 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3219. Min Act: -0.0000

Data Index: 24922 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.2479. Min Act: -0.0001

Data Index: 661817 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.3135. Min Act: -0.0001

Data Index: 310367 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1321195 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.2899. Min Act: -0.0001

Data Index: 276233 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.7320. Min Range: -1.7320

Max Act: 1.0972. Min Act: -0.0000

Data Index: 418709 (C4 (Web Text))

Max Activating Token Index: 687