Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3054 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7303. Min Act: -0.0001

Data Index: 1322644 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6904. Min Act: -0.0001

Data Index: 640966 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6334. Min Act: -0.0001

Data Index: 989608 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6087. Min Act: -0.0001

Data Index: 325820 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6153. Min Act: -0.0001

Data Index: 499778 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6343. Min Act: -0.0001

Data Index: 612123 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6100. Min Act: -0.0001

Data Index: 260679 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6397. Min Act: -0.0001

Data Index: 193842 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6204. Min Act: -0.0001

Data Index: 152858 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6625. Min Act: -0.0001

Data Index: 1174613 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6132. Min Act: -0.0001

Data Index: 1240813 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5738. Min Act: -0.0001

Data Index: 1030129 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5783. Min Act: -0.0001

Data Index: 807667 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5713. Min Act: -0.0001

Data Index: 554330 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1263330 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5519. Min Act: -0.0001

Data Index: 166851 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5693. Min Act: -0.0001

Data Index: 421756 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5699. Min Act: -0.0001

Data Index: 138978 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1004526 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5765. Min Act: -0.0001

Data Index: 829450 (C4 (Web Text))

Max Activating Token Index: 543