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

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

Neuron 1173 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2374. Min Range: -2.2374

Max Act: 2.2374. Min Act: -0.0000

Data Index: 344456 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.6498. Min Act: -0.0000

Data Index: 655446 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 2.2374. Min Range: -2.2374

Max Act: 2.0220. Min Act: -0.0000

Data Index: 1092226 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.8034. Min Act: -0.0000

Data Index: 426624 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.8718. Min Act: -0.0000

Data Index: 540421 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.8151. Min Act: -0.0000

Data Index: 639423 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.6487. Min Act: -0.0000

Data Index: 179678 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.7138. Min Act: -0.0000

Data Index: 578176 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.6225. Min Act: -0.0000

Data Index: 416642 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.8049. Min Act: -0.0000

Data Index: 566934 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.5383. Min Act: -0.0000

Data Index: 679174 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.3497. Min Act: -0.0000

Data Index: 1021473 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.3148. Min Act: -0.0000

Data Index: 496134 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.3234. Min Act: -0.0000

Data Index: 511364 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.2082. Min Act: -0.0000

Data Index: 833718 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.2071. Min Act: -0.0000

Data Index: 810100 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1338995 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1212239 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1294020 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 2.2374. Min Range: -2.2374

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1077673 (C4 (Web Text))

Max Activating Token Index: 39