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

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

Neuron 1657 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1269. Min Range: -1.1269

Max Act: 1.1269. Min Act: -0.0000

Data Index: 581524 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1071614 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.9117. Min Act: -0.0000

Data Index: 927917 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.9671. Min Act: -0.0000

Data Index: 603494 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.8280. Min Act: -0.0000

Data Index: 901264 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1004271 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.8404. Min Act: -0.0000

Data Index: 823563 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.8621. Min Act: 0.0000

Data Index: 254826 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.8154. Min Act: -0.0000

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.8431. Min Act: -0.0000

Data Index: 125413 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.6924. Min Act: -0.0000

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7295. Min Act: -0.0000

Data Index: 199306 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7645. Min Act: -0.0000

Data Index: 613745 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7119. Min Act: -0.0000

Data Index: 416813 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7101. Min Act: 0.0000

Data Index: 1107488 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7268. Min Act: -0.0000

Data Index: 721747 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7218. Min Act: -0.0000

Data Index: 972201 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1116336 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.5950. Min Act: -0.0000

Data Index: 637542 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.1269. Min Range: -1.1269

Max Act: 0.5141. Min Act: -0.0000

Data Index: 180351 (C4 (Web Text))

Max Activating Token Index: 905