Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4242 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.4828. Min Act: -0.0001

Data Index: 675506 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.4662. Min Act: -0.0001

Data Index: 1079828 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.4013. Min Act: -0.0001

Data Index: 459770 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.3393. Min Act: -0.0001

Data Index: 1200210 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.3961. Min Act: -0.0001

Data Index: 713722 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2949. Min Act: -0.0001

Data Index: 509575 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.4305. Min Act: -0.0001

Data Index: 602950 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.3333. Min Act: -0.0001

Data Index: 1165044 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2918. Min Act: -0.0001

Data Index: 83907 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2219. Min Act: -0.0001

Data Index: 1208398 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2742. Min Act: -0.0001

Data Index: 687142 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1326334 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2757. Min Act: -0.0001

Data Index: 875629 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.3108. Min Act: -0.0001

Data Index: 1182035 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2657. Min Act: -0.0001

Data Index: 1302823 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2943. Min Act: -0.0001

Data Index: 184746 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2523. Min Act: -0.0001

Data Index: 44839 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.3655. Min Act: -0.0001

Data Index: 295585 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2933. Min Act: -0.0001

Data Index: 485712 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.4828. Min Range: -1.4828

Max Act: 1.2531. Min Act: -0.0001

Data Index: 188040 (C4 (Web Text))

Max Activating Token Index: 162