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

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

Neuron 1511 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.5484. Min Act: -0.0000

Data Index: 570117 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.4652. Min Act: -0.0000

Data Index: 142228 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.4185. Min Act: -0.0000

Data Index: 550488 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3826. Min Act: -0.0000

Data Index: 904118 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.4066. Min Act: 0.0000

Data Index: 484805 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1311520 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3482. Min Act: -0.0000

Data Index: 208990 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3556. Min Act: -0.0000

Data Index: 172770 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1132705 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3402. Min Act: -0.0000

Data Index: 281462 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1087037 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3623. Min Act: -0.0000

Data Index: 612364 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1218108 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3518. Min Act: -0.0000

Data Index: 238559 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3380. Min Act: -0.0000

Data Index: 402065 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1279027 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3323. Min Act: -0.0000

Data Index: 211917 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1233517 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3299. Min Act: -0.0000

Data Index: 18394 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.5484. Min Range: -0.5484

Max Act: 0.3176. Min Act: -0.0000

Data Index: 59338 (C4 (Web Text))

Max Activating Token Index: 560