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

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

Neuron 1223 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: 0.3238. Min Range: -0.3238

Max Act: 0.3238. Min Act: -0.0001

Data Index: 236419 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2624. Min Act: -0.0001

Data Index: 273865 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3213. Min Act: -0.0001

Data Index: 751107 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3029. Min Act: -0.0001

Data Index: 1257337 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.3010. Min Act: -0.0001

Data Index: 706444 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1152526 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2556. Min Act: -0.0001

Data Index: 1016570 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1229636 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2524. Min Act: -0.0001

Data Index: 926081 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2586. Min Act: -0.0001

Data Index: 894134 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2554. Min Act: -0.0001

Data Index: 1161073 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2682. Min Act: -0.0001

Data Index: 759174 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2576. Min Act: -0.0001

Data Index: 564702 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2375. Min Act: -0.0001

Data Index: 546385 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2737. Min Act: -0.0001

Data Index: 1189353 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2500. Min Act: -0.0001

Data Index: 901452 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2350. Min Act: -0.0001

Data Index: 264837 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1198726 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.1972. Min Act: -0.0001

Data Index: 285695 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.3238. Min Range: -0.3238

Max Act: 0.2406. Min Act: -0.0001

Data Index: 563149 (C4 (Web Text))

Max Activating Token Index: 617