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

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

Neuron 5526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.9943. Min Act: -0.0000

Data Index: 389681 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.9566. Min Act: -0.0000

Data Index: 414194 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.7981. Min Act: -0.0000

Data Index: 111444 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.7965. Min Act: -0.0000

Data Index: 394766 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.7507. Min Act: -0.0000

Data Index: 1134084 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5356. Min Act: -0.0000

Data Index: 749006 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1432643 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6099. Min Act: -0.0000

Data Index: 179707 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5617. Min Act: -0.0000

Data Index: 830961 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5274. Min Act: -0.0000

Data Index: 911145 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1507359 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1109776 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1189636 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1542346 (Python Code)

Max Activating Token Index: 387

Text #14

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1405471 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4751. Min Act: -0.0000

Data Index: 27778 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4761. Min Act: -0.0000

Data Index: 270803 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4790. Min Act: -0.0000

Data Index: 502441 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1196643 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 1.9943. Min Range: -1.9943

Max Act: 1.4550. Min Act: -0.0000

Data Index: 1401794 (Python Code)

Max Activating Token Index: 83