Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1174 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.3775. Min Act: -0.0001

Data Index: 1250823 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1173533 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.4781. Min Act: -0.0001

Data Index: 568235 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2139. Min Act: -0.0001

Data Index: 1297178 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2760. Min Act: -0.0001

Data Index: 1049539 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.3200. Min Act: -0.0001

Data Index: 274213 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1867. Min Act: -0.0001

Data Index: 8343 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2395. Min Act: -0.0001

Data Index: 104618 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1749. Min Act: -0.0001

Data Index: 807452 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2206. Min Act: -0.0001

Data Index: 1267884 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0915. Min Act: -0.0001

Data Index: 904927 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2135. Min Act: -0.0001

Data Index: 415873 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1002. Min Act: -0.0001

Data Index: 94888 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1434. Min Act: -0.0001

Data Index: 1200034 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1619. Min Act: -0.0001

Data Index: 48322 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1756. Min Act: -0.0001

Data Index: 59428 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0705. Min Act: -0.0001

Data Index: 151031 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1343. Min Act: -0.0001

Data Index: 797233 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1849. Min Act: -0.0001

Data Index: 421334 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.4781. Min Range: -1.4781

Max Act: 0.9948. Min Act: -0.0001

Data Index: 1007748 (C4 (Web Text))

Max Activating Token Index: 319