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

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

Neuron 150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1332676 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.8219. Min Act: -0.0001

Data Index: 903349 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7895. Min Act: -0.0001

Data Index: 674717 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7655. Min Act: -0.0001

Data Index: 275307 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7754. Min Act: -0.0001

Data Index: 1208672 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.8166. Min Act: -0.0001

Data Index: 452017 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7649. Min Act: -0.0001

Data Index: 2357 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1024958 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7231. Min Act: -0.0001

Data Index: 111333 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7109. Min Act: -0.0001

Data Index: 389173 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6678. Min Act: -0.0001

Data Index: 219824 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7000. Min Act: -0.0001

Data Index: 525738 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1207404 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1219395 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7249. Min Act: -0.0001

Data Index: 663525 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6564. Min Act: -0.0001

Data Index: 1211178 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7613. Min Act: -0.0001

Data Index: 951184 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7355. Min Act: -0.0001

Data Index: 282284 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.7291. Min Act: -0.0001

Data Index: 224490 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.9008. Min Range: -0.9008

Max Act: 0.6809. Min Act: -0.0001

Data Index: 1324109 (C4 (Web Text))

Max Activating Token Index: 242