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

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

Neuron 1365 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1490. Min Range: -2.1490

Max Act: 2.1257. Min Act: -0.0000

Data Index: 642176 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1207915 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 2.1490. Min Range: -2.1490

Max Act: 2.1490. Min Act: -0.0000

Data Index: 563555 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8718. Min Act: -0.0000

Data Index: 102197 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8172. Min Act: -0.0000

Data Index: 255081 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.7052. Min Act: -0.0000

Data Index: 1148122 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8859. Min Act: -0.0000

Data Index: 187507 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8958. Min Act: -0.0000

Data Index: 323457 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.9829. Min Act: -0.0000

Data Index: 598019 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.6619. Min Act: -0.0000

Data Index: 438716 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1157785 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.7660. Min Act: -0.0000

Data Index: 211425 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8268. Min Act: -0.0000

Data Index: 1321639 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.6067. Min Act: -0.0000

Data Index: 1511777 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.9041. Min Act: -0.0000

Data Index: 244723 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.6985. Min Act: -0.0000

Data Index: 157486 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.7092. Min Act: -0.0000

Data Index: 905352 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1214460 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.7750. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 2.1490. Min Range: -2.1490

Max Act: 1.6078. Min Act: -0.0000

Data Index: 835025 (C4 (Web Text))

Max Activating Token Index: 372