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

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

Neuron 5625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1259. Min Range: -5.1259

Max Act: 5.1259. Min Act: -0.0000

Data Index: 600211 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 5.1259. Min Range: -5.1259

Max Act: 5.1095. Min Act: -0.0000

Data Index: 54402 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.4518. Min Act: -0.0000

Data Index: 1167962 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 5.1259. Min Range: -5.1259

Max Act: 4.1841. Min Act: -0.0000

Data Index: 14086 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.6854. Min Act: -0.0000

Data Index: 217849 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.6872. Min Act: -0.0000

Data Index: 704392 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.6580. Min Act: -0.0000

Data Index: 1164413 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.3876. Min Act: -0.0000

Data Index: 1029300 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.6920. Min Act: -0.0000

Data Index: 676512 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.6491. Min Act: -0.0000

Data Index: 1211589 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.3190. Min Act: -0.0000

Data Index: 645281 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.7874. Min Act: -0.0000

Data Index: 600558 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.5700. Min Act: -0.0000

Data Index: 1279600 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.4451. Min Act: -0.0000

Data Index: 1212054 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.1828. Min Act: -0.0000

Data Index: 492292 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.1548. Min Act: -0.0000

Data Index: 1182946 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.2585. Min Act: -0.0000

Data Index: 392477 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.1215. Min Act: -0.0000

Data Index: 34283 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.1259. Min Range: -5.1259

Max Act: 3.0832. Min Act: -0.0000

Data Index: 1061592 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 5.1259. Min Range: -5.1259

Max Act: 2.9427. Min Act: -0.0000

Data Index: 765778 (C4 (Web Text))

Max Activating Token Index: 829