Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 906 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.9763. Min Act: -0.0001

Data Index: 708590 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.0239. Min Range: -1.0239

Max Act: 1.0239. Min Act: -0.0001

Data Index: 688135 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8299. Min Act: -0.0001

Data Index: 30306 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8262. Min Act: -0.0001

Data Index: 788536 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1025130 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.8188. Min Act: -0.0001

Data Index: 593008 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7576. Min Act: -0.0001

Data Index: 1182614 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7856. Min Act: -0.0001

Data Index: 112194 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7593. Min Act: -0.0001

Data Index: 641607 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7705. Min Act: -0.0001

Data Index: 703995 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1283800 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1006423 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7346. Min Act: -0.0001

Data Index: 240164 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1083692 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7186. Min Act: -0.0001

Data Index: 65532 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.6670. Min Act: -0.0001

Data Index: 334426 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1091898 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.6778. Min Act: -0.0001

Data Index: 143363 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7214. Min Act: -0.0001

Data Index: 580089 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.0239. Min Range: -1.0239

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1194736 (C4 (Web Text))

Max Activating Token Index: 224