Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3078 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.3247. Min Act: -0.0001

Data Index: 368553 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.0658. Min Act: -0.0001

Data Index: 816207 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8957. Min Act: -0.0001

Data Index: 196229 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8586. Min Act: -0.0001

Data Index: 1155387 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8389. Min Act: -0.0001

Data Index: 55290 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7677. Min Act: -0.0001

Data Index: 347034 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8563. Min Act: -0.0001

Data Index: 902701 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8915. Min Act: -0.0001

Data Index: 311361 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7826. Min Act: -0.0001

Data Index: 61767 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7494. Min Act: -0.0001

Data Index: 490063 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7800. Min Act: -0.0001

Data Index: 918763 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7928. Min Act: -0.0001

Data Index: 20131 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7304. Min Act: -0.0001

Data Index: 644695 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7515. Min Act: -0.0001

Data Index: 658 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7116. Min Act: -0.0001

Data Index: 199206 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.6295. Min Act: -0.0001

Data Index: 257557 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.6699. Min Act: -0.0001

Data Index: 1057937 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7266. Min Act: -0.0001

Data Index: 25052 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7368. Min Act: -0.0001

Data Index: 97112 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1271568 (C4 (Web Text))

Max Activating Token Index: 338