Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.7724. Min Act: -0.0000

Data Index: 7642 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.5667. Min Act: -0.0000

Data Index: 454331 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.6989. Min Act: -0.0000

Data Index: 311050 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.6842. Min Act: -0.0000

Data Index: 401405 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.5114. Min Act: -0.0000

Data Index: 185743 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.5445. Min Act: -0.0000

Data Index: 944803 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.4224. Min Act: -0.0000

Data Index: 297125 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.5983. Min Act: -0.0000

Data Index: 458470 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1120410 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1218894 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.4963. Min Act: -0.0000

Data Index: 813464 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.4539. Min Act: -0.0000

Data Index: 1244653 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.4127. Min Act: -0.0000

Data Index: 821172 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.3573. Min Act: -0.0000

Data Index: 69051 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.2595. Min Act: -0.0000

Data Index: 467545 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1066612 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.3138. Min Act: -0.0000

Data Index: 348865 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.2675. Min Act: -0.0000

Data Index: 359591 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1234696 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.7724. Min Range: -1.7724

Max Act: 1.3003. Min Act: -0.0000

Data Index: 478759 (C4 (Web Text))

Max Activating Token Index: 635