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

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

Neuron 1665 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.2399. Min Act: -0.0002

Data Index: 169071 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1077. Min Act: -0.0002

Data Index: 678903 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1174. Min Act: -0.0002

Data Index: 985419 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0852. Min Act: -0.0002

Data Index: 1177467 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0705. Min Act: -0.0002

Data Index: 1217969 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0304. Min Act: -0.0002

Data Index: 843927 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0420. Min Act: -0.0003

Data Index: 194320 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0386. Min Act: -0.0002

Data Index: 1623851 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0390. Min Act: -0.0002

Data Index: 1568480 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0240. Min Act: -0.0002

Data Index: 667472 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0339. Min Act: -0.0002

Data Index: 939958 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0273. Min Act: -0.0002

Data Index: 1624327 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0321. Min Act: -0.0003

Data Index: 1203909 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9952. Min Act: -0.0002

Data Index: 1523767 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9981. Min Act: -0.0002

Data Index: 1057348 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9879. Min Act: -0.0002

Data Index: 802994 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9923. Min Act: -0.0002

Data Index: 808695 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0089. Min Act: -0.0002

Data Index: 1512794 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9788. Min Act: -0.0002

Data Index: 331840 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9836. Min Act: -0.0002

Data Index: 1050114 (C4 (Web Text))

Max Activating Token Index: 377