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

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

Neuron 3167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7411. Min Act: -0.0000

Data Index: 1031306 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7109. Min Act: -0.0000

Data Index: 129806 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.7735. Min Act: -0.0000

Data Index: 895421 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.5889. Min Act: -0.0000

Data Index: 780699 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1164691 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.4068. Min Act: -0.0000

Data Index: 241318 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1257961 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.5645. Min Act: -0.0000

Data Index: 338451 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1068713 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.3541. Min Act: -0.0000

Data Index: 351478 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1215739 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.4717. Min Act: -0.0000

Data Index: 456987 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.3310. Min Act: -0.0000

Data Index: 759093 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1106844 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1076068 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.3612. Min Act: -0.0000

Data Index: 541908 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.2172. Min Act: -0.0000

Data Index: 608505 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.2962. Min Act: -0.0001

Data Index: 337160 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.2811. Min Act: -0.0001

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.7735. Min Range: -1.7735

Max Act: 1.2160. Min Act: -0.0000

Data Index: 363362 (C4 (Web Text))

Max Activating Token Index: 917