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

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

Neuron 4237 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.9794. Min Act: -0.0000

Data Index: 779373 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 3.0487. Min Range: -3.0487

Max Act: 3.0487. Min Act: -0.0000

Data Index: 584586 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.8187. Min Act: -0.0000

Data Index: 947816 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.9543. Min Act: -0.0000

Data Index: 393552 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.7483. Min Act: -0.0000

Data Index: 716981 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.6847. Min Act: -0.0000

Data Index: 19319 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.5286. Min Act: -0.0000

Data Index: 978531 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.6049. Min Act: -0.0000

Data Index: 39085 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.5640. Min Act: -0.0000

Data Index: 705102 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.7007. Min Act: -0.0000

Data Index: 857391 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.6424. Min Act: -0.0000

Data Index: 109 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.4828. Min Act: -0.0000

Data Index: 637958 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.4552. Min Act: -0.0000

Data Index: 728998 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.4365. Min Act: -0.0000

Data Index: 363723 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.4390. Min Act: -0.0000

Data Index: 468363 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.5607. Min Act: -0.0000

Data Index: 276650 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.4165. Min Act: -0.0000

Data Index: 223328 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.5365. Min Act: -0.0000

Data Index: 1301749 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.4066. Min Act: -0.0000

Data Index: 376825 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 3.0487. Min Range: -3.0487

Max Act: 2.3631. Min Act: -0.0000

Data Index: 97853 (C4 (Web Text))

Max Activating Token Index: 1001