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

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

Neuron 2295 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: 3.1753. Min Range: -3.1753

Max Act: 3.1753. Min Act: -0.0001

Data Index: 533594 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.7729. Min Act: -0.0001

Data Index: 529597 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 3.1753. Min Range: -3.1753

Max Act: 3.1121. Min Act: -0.0000

Data Index: 359076 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5483. Min Act: -0.0001

Data Index: 1101003 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.7411. Min Act: -0.0000

Data Index: 963396 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.7550. Min Act: -0.0001

Data Index: 43817 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.7225. Min Act: -0.0001

Data Index: 853570 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5712. Min Act: -0.0001

Data Index: 1322285 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.4545. Min Act: -0.0001

Data Index: 189147 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5449. Min Act: -0.0001

Data Index: 421100 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5452. Min Act: -0.0001

Data Index: 920032 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.6435. Min Act: -0.0001

Data Index: 1344188 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1112626 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5121. Min Act: -0.0000

Data Index: 879774 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.6331. Min Act: -0.0001

Data Index: 490007 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5891. Min Act: -0.0001

Data Index: 418786 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.3664. Min Act: -0.0001

Data Index: 1022942 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.5514. Min Act: -0.0000

Data Index: 740704 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.4136. Min Act: -0.0000

Data Index: 38141 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 3.1753. Min Range: -3.1753

Max Act: 2.3270. Min Act: -0.0001

Data Index: 666584 (C4 (Web Text))

Max Activating Token Index: 351