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

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

Neuron 2812 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: 2.2293. Min Range: -2.2293

Max Act: 2.2293. Min Act: -0.0000

Data Index: 264444 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1153920 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.8751. Min Act: -0.0000

Data Index: 289726 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.8527. Min Act: -0.0000

Data Index: 574182 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.7251. Min Act: -0.0000

Data Index: 1279113 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.6505. Min Act: -0.0000

Data Index: 583762 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.5923. Min Act: -0.0000

Data Index: 229702 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.7610. Min Act: -0.0000

Data Index: 322630 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.7453. Min Act: -0.0000

Data Index: 707006 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.7551. Min Act: -0.0000

Data Index: 188636 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.7048. Min Act: -0.0000

Data Index: 869615 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1306550 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.6023. Min Act: -0.0000

Data Index: 162300 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.6070. Min Act: -0.0000

Data Index: 471779 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.5873. Min Act: -0.0000

Data Index: 973770 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.6674. Min Act: -0.0000

Data Index: 42955 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.5558. Min Act: -0.0000

Data Index: 802011 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.4810. Min Act: -0.0000

Data Index: 1146364 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.4740. Min Act: -0.0000

Data Index: 1133979 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.2293. Min Range: -2.2293

Max Act: 1.5409. Min Act: -0.0000

Data Index: 925698 (C4 (Web Text))

Max Activating Token Index: 966