Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1050565 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2902. Min Act: -0.0001

Data Index: 344676 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2809. Min Act: -0.0000

Data Index: 574672 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2807. Min Act: -0.0000

Data Index: 763629 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2809. Min Act: -0.0001

Data Index: 873998 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2646. Min Act: -0.0001

Data Index: 545404 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1236654 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2659. Min Act: -0.0001

Data Index: 225667 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2522. Min Act: -0.0001

Data Index: 775329 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2408. Min Act: -0.0000

Data Index: 554982 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2458. Min Act: -0.0001

Data Index: 91683 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2459. Min Act: -0.0001

Data Index: 830763 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2453. Min Act: -0.0000

Data Index: 440059 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2541. Min Act: -0.0000

Data Index: 220943 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1056034 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2409. Min Act: -0.0000

Data Index: 430635 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1305310 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2389. Min Act: -0.0000

Data Index: 911317 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1242050 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2281. Min Act: -0.0000

Data Index: 129413 (C4 (Web Text))

Max Activating Token Index: 411