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

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

Neuron 2989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0232. Min Range: -2.0232

Max Act: 2.0232. Min Act: -0.0000

Data Index: 347763 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.7404. Min Act: -0.0000

Data Index: 1250063 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1194708 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4954. Min Act: -0.0000

Data Index: 1351265 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.6201. Min Act: -0.0000

Data Index: 150357 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.6016. Min Act: -0.0000

Data Index: 406039 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.5000. Min Act: -0.0000

Data Index: 355445 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.5041. Min Act: -0.0000

Data Index: 3166 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4783. Min Act: -0.0000

Data Index: 577433 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4704. Min Act: -0.0000

Data Index: 553695 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4547. Min Act: -0.0000

Data Index: 315132 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4603. Min Act: -0.0000

Data Index: 100437 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4507. Min Act: -0.0000

Data Index: 338873 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4288. Min Act: -0.0000

Data Index: 444559 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4142. Min Act: -0.0000

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3351. Min Act: -0.0000

Data Index: 590551 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4140. Min Act: -0.0000

Data Index: 454465 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4167. Min Act: -0.0000

Data Index: 810850 (C4 (Web Text))

Max Activating Token Index: 78