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

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

Neuron 2822 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.7298. Min Act: -0.0001

Data Index: 859320 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.6237. Min Act: -0.0001

Data Index: 377060 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4978. Min Act: -0.0001

Data Index: 1283377 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4490. Min Act: -0.0001

Data Index: 914873 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3868. Min Act: -0.0001

Data Index: 1349771 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3998. Min Act: -0.0001

Data Index: 287651 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3859. Min Act: -0.0001

Data Index: 923117 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.4028. Min Act: -0.0001

Data Index: 1358774 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3956. Min Act: -0.0001

Data Index: 1132967 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3795. Min Act: -0.0001

Data Index: 243234 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3824. Min Act: -0.0001

Data Index: 897633 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3487. Min Act: -0.0001

Data Index: 871191 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3543. Min Act: -0.0001

Data Index: 855717 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.2934. Min Act: -0.0001

Data Index: 963712 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3387. Min Act: -0.0001

Data Index: 643226 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3281. Min Act: -0.0001

Data Index: 327356 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3413. Min Act: -0.0001

Data Index: 335347 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3260. Min Act: -0.0001

Data Index: 410641 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3516. Min Act: -0.0001

Data Index: 721882 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.7298. Min Range: -0.7298

Max Act: 0.3355. Min Act: -0.0001

Data Index: 506450 (C4 (Web Text))

Max Activating Token Index: 986