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

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

Neuron 2809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.9115. Min Act: -0.0000

Data Index: 371799 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.8243. Min Act: -0.0000

Data Index: 151571 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.7828. Min Act: -0.0000

Data Index: 270265 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.7718. Min Act: -0.0000

Data Index: 850820 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.7127. Min Act: -0.0000

Data Index: 915036 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5793. Min Act: -0.0000

Data Index: 316327 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5934. Min Act: -0.0000

Data Index: 195995 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1107865 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1169792 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1070103 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5575. Min Act: -0.0000

Data Index: 616710 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5681. Min Act: -0.0000

Data Index: 610926 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1121749 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5283. Min Act: -0.0000

Data Index: 665563 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5415. Min Act: -0.0000

Data Index: 369884 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1172195 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.4898. Min Act: -0.0000

Data Index: 509956 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.5174. Min Act: -0.0000

Data Index: 885221 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.4970. Min Act: -0.0000

Data Index: 805678 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.9115. Min Range: -0.9115

Max Act: 0.4986. Min Act: -0.0000

Data Index: 424346 (C4 (Web Text))

Max Activating Token Index: 176