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

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

Neuron 629 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: 0.5997. Min Range: -0.5997

Max Act: 0.5997. Min Act: -0.0000

Data Index: 791772 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5447. Min Act: -0.0000

Data Index: 399421 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5408. Min Act: -0.0001

Data Index: 255094 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4508. Min Act: -0.0001

Data Index: 848425 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4858. Min Act: -0.0001

Data Index: 919993 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5187. Min Act: -0.0001

Data Index: 732393 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4953. Min Act: -0.0001

Data Index: 571740 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4780. Min Act: -0.0001

Data Index: 852482 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4555. Min Act: -0.0000

Data Index: 277023 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4060. Min Act: -0.0001

Data Index: 886049 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4367. Min Act: -0.0001

Data Index: 790548 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4292. Min Act: -0.0001

Data Index: 957113 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4215. Min Act: -0.0001

Data Index: 1346935 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4319. Min Act: -0.0000

Data Index: 346068 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4124. Min Act: -0.0001

Data Index: 1281539 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4247. Min Act: -0.0000

Data Index: 303901 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.3985. Min Act: -0.0000

Data Index: 576913 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.3953. Min Act: -0.0001

Data Index: 888488 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4012. Min Act: -0.0001

Data Index: 157922 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4003. Min Act: -0.0001

Data Index: 425196 (C4 (Web Text))

Max Activating Token Index: 190