Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.8157. Min Act: -0.0000

Data Index: 881229 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6081. Min Act: -0.0001

Data Index: 318403 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5579. Min Act: -0.0000

Data Index: 551203 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1309157 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5523. Min Act: -0.0000

Data Index: 923580 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5242. Min Act: -0.0000

Data Index: 420880 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5172. Min Act: -0.0001

Data Index: 370902 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1342655 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5192. Min Act: -0.0001

Data Index: 105450 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4846. Min Act: -0.0000

Data Index: 391709 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4896. Min Act: -0.0000

Data Index: 362106 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4700. Min Act: -0.0000

Data Index: 635093 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5109. Min Act: -0.0001

Data Index: 868568 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4725. Min Act: -0.0001

Data Index: 192247 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1160800 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4459. Min Act: -0.0001

Data Index: 522593 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4555. Min Act: -0.0000

Data Index: 154071 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1184671 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1234190 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1276231 (C4 (Web Text))

Max Activating Token Index: 188