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

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

Neuron 3672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7791. Min Act: -0.0000

Data Index: 829854 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.7473. Min Act: -0.0000

Data Index: 851229 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1157687 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1109178 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5952. Min Act: -0.0000

Data Index: 738732 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.6067. Min Act: -0.0000

Data Index: 512437 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5657. Min Act: -0.0000

Data Index: 263408 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5420. Min Act: -0.0000

Data Index: 490302 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5606. Min Act: -0.0000

Data Index: 753784 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5900. Min Act: -0.0000

Data Index: 131245 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5894. Min Act: -0.0000

Data Index: 272643 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1048970 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5736. Min Act: -0.0001

Data Index: 147988 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5652. Min Act: -0.0000

Data Index: 382642 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1160571 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1149232 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1065649 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5267. Min Act: -0.0000

Data Index: 614303 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1038909 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.7791. Min Range: -0.7791

Max Act: 0.4848. Min Act: -0.0000

Data Index: 495087 (C4 (Web Text))

Max Activating Token Index: 376