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

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

Neuron 3073 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.5242. Min Act: -0.0001

Data Index: 638825 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.2879. Min Act: -0.0001

Data Index: 171550 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1387. Min Act: -0.0001

Data Index: 1127420 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1329. Min Act: -0.0001

Data Index: 840457 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1067039 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0216. Min Act: -0.0001

Data Index: 902252 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0683. Min Act: -0.0001

Data Index: 1093382 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0652. Min Act: -0.0001

Data Index: 871570 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0979. Min Act: -0.0001

Data Index: 746371 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 1.5242. Min Range: -1.5242

Max Act: 0.8737. Min Act: -0.0001

Data Index: 823658 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0266. Min Act: -0.0001

Data Index: 337899 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0836. Min Act: -0.0001

Data Index: 435353 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0172. Min Act: -0.0001

Data Index: 718964 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0743. Min Act: -0.0001

Data Index: 959070 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0263. Min Act: -0.0001

Data Index: 880836 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.5242. Min Range: -1.5242

Max Act: 0.9943. Min Act: -0.0001

Data Index: 1308523 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.5242. Min Range: -1.5242

Max Act: 0.9229. Min Act: -0.0001

Data Index: 77042 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.5242. Min Range: -1.5242

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1250855 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.5242. Min Range: -1.5242

Max Act: 0.9773. Min Act: -0.0001

Data Index: 492948 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.5242. Min Range: -1.5242

Max Act: 1.0000. Min Act: -0.0001

Data Index: 793565 (C4 (Web Text))

Max Activating Token Index: 120