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

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

Neuron 3436 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.6560. Min Act: -0.0002

Data Index: 701792 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.5699. Min Act: -0.0002

Data Index: 1022694 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.4473. Min Act: -0.0001

Data Index: 316322 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.5424. Min Act: -0.0001

Data Index: 412368 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.4828. Min Act: -0.0001

Data Index: 1345274 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.4703. Min Act: -0.0001

Data Index: 902693 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.4118. Min Act: -0.0002

Data Index: 1301126 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2452. Min Act: -0.0001

Data Index: 244680 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3305. Min Act: -0.0001

Data Index: 546753 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3235. Min Act: -0.0001

Data Index: 1265221 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3207. Min Act: -0.0001

Data Index: 719856 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2844. Min Act: -0.0001

Data Index: 598334 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3197. Min Act: -0.0001

Data Index: 514269 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.1946. Min Act: -0.0001

Data Index: 718060 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3437. Min Act: -0.0001

Data Index: 1224314 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2580. Min Act: -0.0001

Data Index: 609873 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2542. Min Act: -0.0001

Data Index: 303631 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3779. Min Act: -0.0001

Data Index: 125788 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.3161. Min Act: -0.0001

Data Index: 1175162 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.6560. Min Range: -1.6560

Max Act: 1.2058. Min Act: -0.0001

Data Index: 84436 (C4 (Web Text))

Max Activating Token Index: 160