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

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

Neuron 1281 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: 0.5134. Min Range: -0.5134

Max Act: 0.5134. Min Act: -0.0000

Data Index: 322840 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1167843 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1284296 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.3652. Min Act: -0.0000

Data Index: 698103 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.3660. Min Act: 0.0001

Data Index: 371551 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.3524. Min Act: -0.0000

Data Index: 776241 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.3117. Min Act: 0.0001

Data Index: 209182 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.3024. Min Act: -0.0000

Data Index: 68662 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.3015. Min Act: 0.0001

Data Index: 678947 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2973. Min Act: -0.0000

Data Index: 443736 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2943. Min Act: -0.0000

Data Index: 464618 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1341787 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2617. Min Act: 0.0000

Data Index: 618809 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2783. Min Act: -0.0000

Data Index: 591400 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1115202 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1339634 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2717. Min Act: 0.0000

Data Index: 14728 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2623. Min Act: 0.0000

Data Index: 1139843 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2700. Min Act: 0.0000

Data Index: 1196639 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.2544. Min Act: 0.0000

Data Index: 1226457 (C4 (Web Text))

Max Activating Token Index: 983