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

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

Neuron 5584 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1512. Min Range: -1.1512

Max Act: 1.1512. Min Act: -0.0000

Data Index: 774198 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.1512. Min Range: -1.1512

Max Act: 1.1410. Min Act: -0.0000

Data Index: 121305 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.1512. Min Range: -1.1512

Max Act: 1.0172. Min Act: 0.0000

Data Index: 164545 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.9858. Min Act: -0.0000

Data Index: 449345 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1036354 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.9067. Min Act: -0.0000

Data Index: 53071 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.8832. Min Act: 0.0000

Data Index: 318879 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.9435. Min Act: -0.0000

Data Index: 970240 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1337192 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.9156. Min Act: -0.0000

Data Index: 584875 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1300692 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1202323 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.8271. Min Act: -0.0000

Data Index: 200853 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.8302. Min Act: -0.0000

Data Index: 594076 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.8046. Min Act: -0.0000

Data Index: 41219 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1279097 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.7448. Min Act: -0.0000

Data Index: 81136 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.7221. Min Act: -0.0000

Data Index: 436924 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.7353. Min Act: -0.0000

Data Index: 124730 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.1512. Min Range: -1.1512

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1273002 (C4 (Web Text))

Max Activating Token Index: 741