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

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

Neuron 372 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: 1.2193. Min Range: -1.2193

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1180 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0720. Min Act: -0.0001

Data Index: 1135801 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9952. Min Act: -0.0001

Data Index: 1348150 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.2193. Min Act: -0.0001

Data Index: 557033 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.1441. Min Act: -0.0001

Data Index: 1115221 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0053. Min Act: -0.0001

Data Index: 433042 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0296. Min Act: -0.0001

Data Index: 677731 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0804. Min Act: -0.0001

Data Index: 881468 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.1281. Min Act: -0.0000

Data Index: 564033 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.8011. Min Act: -0.0001

Data Index: 684050 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9701. Min Act: -0.0001

Data Index: 1274000 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9706. Min Act: -0.0001

Data Index: 42226 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9687. Min Act: -0.0001

Data Index: 78529 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9114. Min Act: -0.0001

Data Index: 868472 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9165. Min Act: -0.0001

Data Index: 579292 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0068. Min Act: -0.0001

Data Index: 371512 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.8623. Min Act: -0.0001

Data Index: 81083 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.2193. Min Range: -1.2193

Max Act: 1.0289. Min Act: -0.0001

Data Index: 5122 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9400. Min Act: -0.0001

Data Index: 1171606 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.2193. Min Range: -1.2193

Max Act: 0.9331. Min Act: -0.0001

Data Index: 903752 (C4 (Web Text))

Max Activating Token Index: 158