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

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

Neuron 1158 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1288613 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.3598. Min Act: -0.0000

Data Index: 171042 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.5587. Min Act: -0.0000

Data Index: 1035502 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.3076. Min Act: -0.0000

Data Index: 951621 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2882. Min Act: -0.0000

Data Index: 413640 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2452. Min Act: -0.0000

Data Index: 73425 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1225696 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1853. Min Act: -0.0000

Data Index: 646915 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1257745 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1310. Min Act: -0.0000

Data Index: 104557 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0680. Min Act: -0.0000

Data Index: 526161 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0654. Min Act: -0.0000

Data Index: 282005 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1117. Min Act: -0.0000

Data Index: 576563 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0434. Min Act: -0.0000

Data Index: 874691 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.5587. Min Range: -1.5587

Max Act: 0.9687. Min Act: -0.0000

Data Index: 528068 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1144009 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0220. Min Act: -0.0000

Data Index: 192688 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0983. Min Act: -0.0000

Data Index: 132674 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1093321 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.5587. Min Range: -1.5587

Max Act: 0.9946. Min Act: -0.0000

Data Index: 873334 (C4 (Web Text))

Max Activating Token Index: 154