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

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

Neuron 2479 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: 0.7927. Min Range: -0.7927

Max Act: 0.7927. Min Act: -0.0001

Data Index: 718627 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1062027 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.5376. Min Act: -0.0001

Data Index: 307069 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4985. Min Act: -0.0001

Data Index: 365215 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4768. Min Act: -0.0001

Data Index: 401691 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4533. Min Act: -0.0000

Data Index: 957224 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4355. Min Act: -0.0001

Data Index: 634484 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1025845 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4784. Min Act: -0.0000

Data Index: 836143 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4318. Min Act: -0.0001

Data Index: 153378 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4758. Min Act: -0.0000

Data Index: 89964 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4287. Min Act: -0.0001

Data Index: 240020 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4262. Min Act: -0.0000

Data Index: 336604 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4245. Min Act: -0.0001

Data Index: 657118 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4315. Min Act: -0.0000

Data Index: 517577 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1180882 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4173. Min Act: -0.0001

Data Index: 220181 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4013. Min Act: -0.0000

Data Index: 838403 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4177. Min Act: -0.0000

Data Index: 924528 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.7927. Min Range: -0.7927

Max Act: 0.4156. Min Act: -0.0000

Data Index: 70985 (C4 (Web Text))

Max Activating Token Index: 381