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

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

Neuron 2883 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1195. Min Range: -3.1195

Max Act: 3.1195. Min Act: -0.0000

Data Index: 851770 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.4070. Min Act: -0.0000

Data Index: 972351 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.6269. Min Act: -0.0000

Data Index: 529516 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.4511. Min Act: -0.0000

Data Index: 207121 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.5392. Min Act: -0.0000

Data Index: 1051355 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.2703. Min Act: -0.0000

Data Index: 473023 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.3838. Min Act: -0.0000

Data Index: 408131 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.3598. Min Act: -0.0000

Data Index: 28476 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.1148. Min Act: -0.0000

Data Index: 139426 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.3210. Min Act: -0.0000

Data Index: 666257 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 3.1195. Min Range: -3.1195

Max Act: 1.8758. Min Act: -0.0000

Data Index: 740988 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.5404. Min Act: -0.0000

Data Index: 259191 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.3031. Min Act: -0.0000

Data Index: 1100600 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.2555. Min Act: -0.0000

Data Index: 410179 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.2676. Min Act: -0.0000

Data Index: 135273 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.2444. Min Act: -0.0000

Data Index: 949044 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.3674. Min Act: -0.0000

Data Index: 785125 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.2337. Min Act: -0.0000

Data Index: 1202652 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.3396. Min Act: -0.0000

Data Index: 1045884 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 3.1195. Min Range: -3.1195

Max Act: 2.0930. Min Act: -0.0000

Data Index: 783404 (C4 (Web Text))

Max Activating Token Index: 112