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

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

Neuron 3387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1255360 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6368. Min Act: -0.0001

Data Index: 933191 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1347956 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1260615 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6198. Min Act: -0.0001

Data Index: 162237 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6003. Min Act: -0.0001

Data Index: 740451 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6173. Min Act: -0.0001

Data Index: 759264 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1045345 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5812. Min Act: -0.0001

Data Index: 966911 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6201. Min Act: -0.0001

Data Index: 68206 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5939. Min Act: -0.0001

Data Index: 1123693 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5779. Min Act: -0.0001

Data Index: 245716 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5880. Min Act: -0.0001

Data Index: 756448 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5566. Min Act: -0.0001

Data Index: 564771 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5841. Min Act: -0.0001

Data Index: 1284944 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5641. Min Act: -0.0001

Data Index: 1220782 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5465. Min Act: -0.0001

Data Index: 430755 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5296. Min Act: -0.0001

Data Index: 65177 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5560. Min Act: -0.0001

Data Index: 272370 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5564. Min Act: -0.0001

Data Index: 690394 (C4 (Web Text))

Max Activating Token Index: 400