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

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

Neuron 1607 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2988. Min Act: -0.0000

Data Index: 796852 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3524. Min Act: -0.0000

Data Index: 19966 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1113286 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3211. Min Act: -0.0000

Data Index: 769992 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3156. Min Act: -0.0000

Data Index: 892608 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2904. Min Act: -0.0000

Data Index: 782791 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3426. Min Act: -0.0000

Data Index: 533976 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3089. Min Act: -0.0000

Data Index: 547759 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3152. Min Act: -0.0000

Data Index: 195486 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2988. Min Act: -0.0000

Data Index: 968759 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1300385 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3178. Min Act: -0.0000

Data Index: 203143 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2872. Min Act: -0.0000

Data Index: 147711 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3060. Min Act: -0.0000

Data Index: 976593 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3032. Min Act: -0.0000

Data Index: 902042 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3146. Min Act: -0.0000

Data Index: 515391 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.2900. Min Act: -0.0000

Data Index: 591328 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1352017 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3147. Min Act: -0.0000

Data Index: 53307 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.3524. Min Range: -0.3524

Max Act: 0.3037. Min Act: -0.0000

Data Index: 533134 (C4 (Web Text))

Max Activating Token Index: 876