Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1550 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0004

Data Index: 1080987 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0344. Min Act: -0.0004

Data Index: 673758 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0335. Min Act: -0.0004

Data Index: 830981 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0323. Min Act: -0.0004

Data Index: 571129 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0309. Min Act: -0.0004

Data Index: 1092108 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0319. Min Act: -0.0004

Data Index: 553914 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0293. Min Act: -0.0004

Data Index: 107431 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0299. Min Act: -0.0005

Data Index: 30758 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0297. Min Act: -0.0004

Data Index: 39701 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0290. Min Act: -0.0004

Data Index: 756385 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0298. Min Act: -0.0004

Data Index: 893946 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0288. Min Act: -0.0004

Data Index: 238477 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0287. Min Act: -0.0004

Data Index: 26758 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0285. Min Act: -0.0004

Data Index: 84760 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1066423 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0275. Min Act: -0.0004

Data Index: 593079 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0287. Min Act: -0.0004

Data Index: 506003 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0286. Min Act: -0.0004

Data Index: 985953 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0275. Min Act: -0.0004

Data Index: 1116138 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0279. Min Act: -0.0004

Data Index: 694826 (C4 (Web Text))

Max Activating Token Index: 333