Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1779 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.5175. Min Act: -0.0005

Data Index: 1064148 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4800. Min Act: -0.0005

Data Index: 1287999 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4108. Min Act: -0.0005

Data Index: 73738 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4272. Min Act: -0.0005

Data Index: 283934 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4370. Min Act: -0.0005

Data Index: 473897 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4325. Min Act: -0.0005

Data Index: 372903 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3757. Min Act: -0.0005

Data Index: 959007 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4018. Min Act: -0.0005

Data Index: 1204489 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3868. Min Act: -0.0005

Data Index: 243492 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3931. Min Act: -0.0005

Data Index: 175025 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4166. Min Act: -0.0005

Data Index: 1006296 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3855. Min Act: -0.0005

Data Index: 1269956 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3746. Min Act: -0.0005

Data Index: 39200 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3725. Min Act: -0.0005

Data Index: 137164 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3630. Min Act: -0.0005

Data Index: 1064173 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3611. Min Act: -0.0005

Data Index: 946392 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3503. Min Act: -0.0005

Data Index: 499879 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3605. Min Act: -0.0005

Data Index: 417615 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3770. Min Act: -0.0005

Data Index: 787146 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3490. Min Act: -0.0005

Data Index: 1074477 (C4 (Web Text))

Max Activating Token Index: 737