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

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

Neuron 2820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4676. Min Range: -4.4676

Max Act: 4.4676. Min Act: -0.0000

Data Index: 353376 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.9220. Min Act: -0.0000

Data Index: 319184 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.5241. Min Act: -0.0000

Data Index: 1260298 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.4495. Min Act: -0.0000

Data Index: 2863 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.3175. Min Act: -0.0000

Data Index: 867835 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.9325. Min Act: -0.0000

Data Index: 845510 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.9994. Min Act: -0.0000

Data Index: 1244106 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.1213. Min Act: -0.0000

Data Index: 945533 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 4.4676. Min Range: -4.4676

Max Act: 3.1390. Min Act: -0.0000

Data Index: 103874 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.7360. Min Act: -0.0000

Data Index: 546923 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.6913. Min Act: -0.0000

Data Index: 465495 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.5908. Min Act: -0.0000

Data Index: 551249 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.7146. Min Act: -0.0000

Data Index: 254209 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.6937. Min Act: -0.0000

Data Index: 385708 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.6492. Min Act: -0.0000

Data Index: 561760 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.4577. Min Act: -0.0000

Data Index: 315628 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.3211. Min Act: -0.0000

Data Index: 667830 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.3496. Min Act: -0.0000

Data Index: 891971 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.2650. Min Act: -0.0000

Data Index: 987657 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 4.4676. Min Range: -4.4676

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1133511 (C4 (Web Text))

Max Activating Token Index: 559