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

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

Neuron 3420 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: 1.0524. Min Range: -1.0524

Max Act: 1.0447. Min Act: -0.0000

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 1.0524. Min Range: -1.0524

Max Act: 1.0524. Min Act: -0.0000

Data Index: 428114 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.8986. Min Act: -0.0000

Data Index: 757975 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1173701 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1144935 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.7698. Min Act: -0.0000

Data Index: 176939 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1183715 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.6539. Min Act: -0.0000

Data Index: 37281 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1042992 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1240732 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1287285 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4672. Min Act: -0.0000

Data Index: 623562 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4811. Min Act: -0.0000

Data Index: 354024 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4956. Min Act: -0.0000

Data Index: 962697 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4860. Min Act: -0.0000

Data Index: 827652 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4765. Min Act: -0.0000

Data Index: 20184 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4815. Min Act: -0.0000

Data Index: 758140 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4682. Min Act: -0.0000

Data Index: 553849 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4417. Min Act: -0.0000

Data Index: 124912 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.0524. Min Range: -1.0524

Max Act: 0.4676. Min Act: -0.0000

Data Index: 504114 (C4 (Web Text))

Max Activating Token Index: 642