Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.8048. Min Act: -0.0001

Data Index: 322484 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.7428. Min Act: -0.0001

Data Index: 457197 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.7693. Min Act: -0.0001

Data Index: 359223 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.7503. Min Act: -0.0001

Data Index: 705668 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6946. Min Act: -0.0001

Data Index: 326241 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5242. Min Act: -0.0001

Data Index: 1118516 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6391. Min Act: -0.0001

Data Index: 659894 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5429. Min Act: -0.0001

Data Index: 904114 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5384. Min Act: -0.0001

Data Index: 592671 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5725. Min Act: -0.0001

Data Index: 845559 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5080. Min Act: -0.0001

Data Index: 128428 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.4849. Min Act: -0.0001

Data Index: 1046670 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.6385. Min Act: -0.0001

Data Index: 155041 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.4563. Min Act: -0.0001

Data Index: 1286704 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5504. Min Act: -0.0001

Data Index: 749971 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.5257. Min Act: -0.0001

Data Index: 192080 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.3524. Min Act: -0.0001

Data Index: 646861 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.4815. Min Act: -0.0001

Data Index: 113447 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.4852. Min Act: -0.0001

Data Index: 877340 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.8048. Min Range: -1.8048

Max Act: 1.3966. Min Act: -0.0001

Data Index: 28020 (C4 (Web Text))

Max Activating Token Index: 159