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

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

Neuron 2561 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5697. Min Range: -7.5697

Max Act: 7.3314. Min Act: -0.0000

Data Index: 526304 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 7.5697. Min Range: -7.5697

Max Act: 7.5697. Min Act: -0.0000

Data Index: 297494 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 7.5697. Min Range: -7.5697

Max Act: 7.0767. Min Act: -0.0000

Data Index: 416778 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 7.5697. Min Range: -7.5697

Max Act: 7.0647. Min Act: -0.0000

Data Index: 154294 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.9313. Min Act: -0.0000

Data Index: 393402 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.6893. Min Act: -0.0000

Data Index: 212102 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.5527. Min Act: -0.0000

Data Index: 231287 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.1952. Min Act: -0.0000

Data Index: 886277 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.3481. Min Act: -0.0000

Data Index: 844196 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.1571. Min Act: -0.0000

Data Index: 1192724 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.1127. Min Act: -0.0000

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.2426. Min Act: -0.0000

Data Index: 222073 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 7.5697. Min Range: -7.5697

Max Act: 6.3153. Min Act: -0.0000

Data Index: 1150670 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.7726. Min Act: -0.0000

Data Index: 191782 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.9279. Min Act: -0.0000

Data Index: 426726 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.8374. Min Act: -0.0000

Data Index: 662192 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.9688. Min Act: -0.0000

Data Index: 314307 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.8030. Min Act: -0.0000

Data Index: 290420 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.7980. Min Act: -0.0000

Data Index: 192148 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 7.5697. Min Range: -7.5697

Max Act: 5.9476. Min Act: -0.0000

Data Index: 705406 (C4 (Web Text))

Max Activating Token Index: 346