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

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

Neuron 1679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.1774. Min Act: -0.0000

Data Index: 840512 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.2394. Min Act: -0.0000

Data Index: 77602 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.2031. Min Act: -0.0000

Data Index: 578192 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.1859. Min Act: -0.0000

Data Index: 433776 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.0536. Min Act: -0.0000

Data Index: 431563 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.9926. Min Act: -0.0000

Data Index: 374910 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1107572 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1131860 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.0177. Min Act: -0.0000

Data Index: 589425 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1025096 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.2394. Min Range: -1.2394

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1065225 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.9011. Min Act: -0.0000

Data Index: 183416 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.8907. Min Act: -0.0000

Data Index: 792318 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.8778. Min Act: -0.0000

Data Index: 199930 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.8637. Min Act: -0.0000

Data Index: 516238 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.9030. Min Act: -0.0000

Data Index: 230486 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.9041. Min Act: -0.0000

Data Index: 588625 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.8896. Min Act: -0.0000

Data Index: 183012 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.8318. Min Act: -0.0000

Data Index: 148373 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.2394. Min Range: -1.2394

Max Act: 0.9366. Min Act: -0.0000

Data Index: 194496 (C4 (Web Text))

Max Activating Token Index: 200