Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1205 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.5623. Min Act: -0.0003

Data Index: 1265322 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4499. Min Act: -0.0003

Data Index: 1185905 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4501. Min Act: -0.0003

Data Index: 857743 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4584. Min Act: -0.0003

Data Index: 1310653 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4873. Min Act: -0.0003

Data Index: 1184152 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4543. Min Act: -0.0003

Data Index: 180349 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3925. Min Act: -0.0003

Data Index: 496212 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4498. Min Act: -0.0003

Data Index: 361061 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4180. Min Act: -0.0003

Data Index: 863332 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3993. Min Act: -0.0003

Data Index: 293429 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4321. Min Act: -0.0003

Data Index: 1139370 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4180. Min Act: -0.0003

Data Index: 237266 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4018. Min Act: -0.0003

Data Index: 999202 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3849. Min Act: -0.0003

Data Index: 926455 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4006. Min Act: -0.0003

Data Index: 1005313 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3903. Min Act: -0.0003

Data Index: 1204817 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4093. Min Act: -0.0003

Data Index: 137717 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4190. Min Act: -0.0003

Data Index: 494529 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3945. Min Act: -0.0003

Data Index: 1072805 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3890. Min Act: -0.0003

Data Index: 850277 (C4 (Web Text))

Max Activating Token Index: 1002