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

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

Neuron 2513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1100093 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1264911 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5960. Min Act: -0.0001

Data Index: 1148807 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5962. Min Act: -0.0001

Data Index: 543278 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5932. Min Act: -0.0001

Data Index: 767339 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5800. Min Act: -0.0001

Data Index: 253434 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5805. Min Act: -0.0001

Data Index: 216556 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1353590 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5915. Min Act: -0.0001

Data Index: 280295 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5881. Min Act: -0.0001

Data Index: 1067262 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.6004. Min Act: -0.0001

Data Index: 1356279 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5646. Min Act: -0.0001

Data Index: 965858 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5738. Min Act: -0.0001

Data Index: 581153 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5728. Min Act: -0.0001

Data Index: 886241 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5742. Min Act: -0.0001

Data Index: 88552 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5623. Min Act: -0.0001

Data Index: 790456 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5262. Min Act: -0.0001

Data Index: 3775 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5223. Min Act: -0.0001

Data Index: 140045 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5539. Min Act: -0.0001

Data Index: 620155 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.6298. Min Range: -0.6298

Max Act: 0.5683. Min Act: -0.0001

Data Index: 851239 (C4 (Web Text))

Max Activating Token Index: 686