Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1152 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.5994. Min Act: -0.0000

Data Index: 645778 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.5581. Min Act: -0.0000

Data Index: 1270783 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1288582 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1069829 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.2390. Min Act: -0.0000

Data Index: 462276 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1288398 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.2944. Min Act: -0.0000

Data Index: 379819 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1702. Min Act: -0.0000

Data Index: 338562 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.2454. Min Act: -0.0000

Data Index: 362431 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1579. Min Act: -0.0000

Data Index: 285060 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1309634 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1195693 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1004. Min Act: -0.0000

Data Index: 153426 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1301. Min Act: -0.0000

Data Index: 538850 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.2549. Min Act: -0.0000

Data Index: 280053 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1065. Min Act: -0.0000

Data Index: 390764 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1661. Min Act: -0.0000

Data Index: 325732 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1678. Min Act: 0.0000

Data Index: 871310 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1677. Min Act: -0.0000

Data Index: 614714 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1077. Min Act: -0.0000

Data Index: 850139 (C4 (Web Text))

Max Activating Token Index: 107