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

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

Neuron 370 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: 2.4524. Min Range: -2.4524

Max Act: 2.4524. Min Act: -0.0000

Data Index: 917264 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 2.4524. Min Range: -2.4524

Max Act: 2.3344. Min Act: -0.0000

Data Index: 276017 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.7924. Min Act: -0.0000

Data Index: 199590 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.6885. Min Act: -0.0000

Data Index: 905342 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.4061. Min Act: -0.0000

Data Index: 729631 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.3480. Min Act: -0.0000

Data Index: 692027 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.3894. Min Act: -0.0000

Data Index: 635446 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.3141. Min Act: -0.0000

Data Index: 83367 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.3221. Min Act: -0.0000

Data Index: 897881 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.2123. Min Act: -0.0000

Data Index: 173249 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1811. Min Act: -0.0000

Data Index: 174749 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1919. Min Act: -0.0000

Data Index: 819798 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1721. Min Act: -0.0000

Data Index: 859804 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1294. Min Act: -0.0000

Data Index: 468511 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1322. Min Act: -0.0000

Data Index: 616138 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1585. Min Act: -0.0000

Data Index: 272679 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1712. Min Act: -0.0000

Data Index: 620613 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1019101 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1264554 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 2.4524. Min Range: -2.4524

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1247369 (C4 (Web Text))

Max Activating Token Index: 319