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

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

Neuron 1 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: 3.4311. Min Range: -3.4311

Max Act: 3.4311. Min Act: -0.0000

Data Index: 353827 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.6345. Min Act: -0.0000

Data Index: 945371 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.6655. Min Act: -0.0000

Data Index: 1206712 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.2311. Min Act: -0.0000

Data Index: 418215 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.3273. Min Act: -0.0000

Data Index: 800021 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.1943. Min Act: -0.0000

Data Index: 108050 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.1617. Min Act: -0.0000

Data Index: 964692 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.3216. Min Act: -0.0000

Data Index: 1351175 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.0487. Min Act: -0.0000

Data Index: 664876 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 3.4311. Min Range: -3.4311

Max Act: 1.9845. Min Act: -0.0000

Data Index: 1106517 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.1093. Min Act: -0.0000

Data Index: 146673 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.1994. Min Act: -0.0000

Data Index: 269439 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.1647. Min Act: -0.0000

Data Index: 840868 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.1405. Min Act: -0.0000

Data Index: 676431 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.4311. Min Range: -3.4311

Max Act: 1.8883. Min Act: -0.0000

Data Index: 635352 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.0930. Min Act: -0.0000

Data Index: 1215964 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 3.4311. Min Range: -3.4311

Max Act: 1.9797. Min Act: -0.0000

Data Index: 514185 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 3.4311. Min Range: -3.4311

Max Act: 2.0693. Min Act: -0.0000

Data Index: 1107375 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.4311. Min Range: -3.4311

Max Act: 1.7158. Min Act: -0.0000

Data Index: 448995 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 3.4311. Min Range: -3.4311

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1208729 (C4 (Web Text))

Max Activating Token Index: 940