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

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

Neuron 2734 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: 0.6265. Min Range: -0.6265

Max Act: 0.6265. Min Act: -0.0000

Data Index: 849020 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5399. Min Act: -0.0000

Data Index: 519238 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5058. Min Act: -0.0000

Data Index: 853676 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4517. Min Act: -0.0000

Data Index: 248358 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5251. Min Act: -0.0000

Data Index: 6769 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5597. Min Act: -0.0000

Data Index: 809198 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4574. Min Act: -0.0000

Data Index: 475822 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5102. Min Act: -0.0000

Data Index: 988835 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.3901. Min Act: -0.0000

Data Index: 167637 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4613. Min Act: -0.0000

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1133278 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4606. Min Act: -0.0000

Data Index: 874308 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4701. Min Act: -0.0000

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4622. Min Act: -0.0000

Data Index: 339792 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5202. Min Act: -0.0000

Data Index: 68047 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4318. Min Act: -0.0000

Data Index: 723832 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1259583 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.3892. Min Act: -0.0000

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1035006 (C4 (Web Text))

Max Activating Token Index: 841