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

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

Neuron 1726 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3796. Min Act: -0.0000

Data Index: 480927 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3432. Min Act: -0.0001

Data Index: 667150 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3169. Min Act: -0.0001

Data Index: 1003328 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3202. Min Act: -0.0000

Data Index: 402955 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2980. Min Act: -0.0000

Data Index: 782993 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1230512 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1322718 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1075714 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1208903 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2663. Min Act: -0.0001

Data Index: 550833 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2582. Min Act: -0.0001

Data Index: 187962 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2604. Min Act: -0.0000

Data Index: 708462 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1288965 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2626. Min Act: -0.0001

Data Index: 185382 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1292717 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2506. Min Act: 0.0001

Data Index: 10726 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2509. Min Act: -0.0000

Data Index: 390565 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2379. Min Act: -0.0001

Data Index: 820090 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2387. Min Act: -0.0000

Data Index: 283741 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2390. Min Act: -0.0001

Data Index: 836198 (C4 (Web Text))

Max Activating Token Index: 87