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

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

Neuron 6076 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0521. Min Act: -0.0002

Data Index: 785744 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0422. Min Act: -0.0002

Data Index: 499947 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1322271 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0401. Min Act: -0.0002

Data Index: 274916 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0390. Min Act: -0.0002

Data Index: 32486 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1649424 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0394. Min Act: -0.0002

Data Index: 439726 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1612484 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1102629 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0381. Min Act: -0.0002

Data Index: 332945 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0373. Min Act: -0.0002

Data Index: 670918 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1416710 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0360. Min Act: -0.0002

Data Index: 825630 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0372. Min Act: -0.0002

Data Index: 74466 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1474302 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0351. Min Act: -0.0002

Data Index: 425576 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0351. Min Act: -0.0002

Data Index: 945133 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1633117 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1649933 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0354. Min Act: -0.0002

Data Index: 433358 (C4 (Web Text))

Max Activating Token Index: 793