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

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

Neuron 4177 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: 3.3655. Min Range: -3.3655

Max Act: 3.3655. Min Act: -0.0000

Data Index: 1194264 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 3.3655. Min Range: -3.3655

Max Act: 3.0741. Min Act: -0.0000

Data Index: 1337938 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.7471. Min Act: -0.0000

Data Index: 548689 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.5404. Min Act: -0.0000

Data Index: 1134040 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1045870 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.5396. Min Act: -0.0000

Data Index: 385159 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.6654. Min Act: -0.0000

Data Index: 1027727 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.6263. Min Act: -0.0000

Data Index: 1183924 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.4848. Min Act: -0.0000

Data Index: 165678 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.4606. Min Act: -0.0000

Data Index: 823690 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.5847. Min Act: -0.0000

Data Index: 272994 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1156846 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.5240. Min Act: -0.0000

Data Index: 882599 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.3443. Min Act: -0.0000

Data Index: 1030711 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.3300. Min Act: -0.0000

Data Index: 252640 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.2934. Min Act: -0.0000

Data Index: 672954 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1279110 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.2677. Min Act: -0.0000

Data Index: 1092993 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.1207. Min Act: -0.0000

Data Index: 310219 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 3.3655. Min Range: -3.3655

Max Act: 2.2219. Min Act: -0.0000

Data Index: 570177 (C4 (Web Text))

Max Activating Token Index: 994