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

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

Neuron 258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.5169. Min Act: -0.0000

Data Index: 1168362 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.3268. Min Act: -0.0000

Data Index: 797393 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.2371. Min Act: -0.0001

Data Index: 1144414 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.2300. Min Act: -0.0001

Data Index: 1310042 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.2270. Min Act: -0.0001

Data Index: 158448 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.1152. Min Act: -0.0001

Data Index: 641026 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.1557. Min Act: -0.0001

Data Index: 359790 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.1453. Min Act: -0.0001

Data Index: 892158 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.1134. Min Act: -0.0001

Data Index: 99611 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.0533. Min Act: -0.0001

Data Index: 694501 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.1072. Min Act: -0.0001

Data Index: 1248858 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.2147. Min Act: -0.0001

Data Index: 495789 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.0389. Min Act: -0.0001

Data Index: 437507 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.5169. Min Range: -1.5169

Max Act: 1.1057. Min Act: -0.0001

Data Index: 477680 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.5169. Min Range: -1.5169

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1089720 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.5169. Min Range: -1.5169

Max Act: 0.9578. Min Act: -0.0001

Data Index: 115134 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.5169. Min Range: -1.5169

Max Act: 0.9706. Min Act: -0.0001

Data Index: 98336 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 1.5169. Min Range: -1.5169

Max Act: 0.9185. Min Act: -0.0001

Data Index: 279636 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.5169. Min Range: -1.5169

Max Act: 0.9503. Min Act: -0.0001

Data Index: 140102 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 1.5169. Min Range: -1.5169

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1048506 (C4 (Web Text))

Max Activating Token Index: 72