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

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

Neuron 1102 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: 2.8759. Min Range: -2.8759

Max Act: 2.8759. Min Act: -0.0000

Data Index: 337218 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.7752. Min Act: -0.0000

Data Index: 1346982 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.6065. Min Act: -0.0000

Data Index: 1184426 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.5662. Min Act: -0.0000

Data Index: 1211249 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.5525. Min Act: -0.0000

Data Index: 1245363 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.5182. Min Act: -0.0000

Data Index: 340926 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.3942. Min Act: -0.0000

Data Index: 505465 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.1975. Min Act: -0.0000

Data Index: 381297 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.2926. Min Act: -0.0000

Data Index: 496544 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.2897. Min Act: -0.0000

Data Index: 48003 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.1766. Min Act: -0.0000

Data Index: 966902 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.0271. Min Act: -0.0000

Data Index: 237745 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.0877. Min Act: -0.0000

Data Index: 185115 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.0596. Min Act: -0.0000

Data Index: 736446 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 2.8759. Min Range: -2.8759

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1213484 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.1334. Min Act: -0.0000

Data Index: 1050485 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.0172. Min Act: -0.0000

Data Index: 276079 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.8759. Min Range: -2.8759

Max Act: 2.0985. Min Act: -0.0000

Data Index: 44924 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 2.8759. Min Range: -2.8759

Max Act: 1.8862. Min Act: -0.0000

Data Index: 894622 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 2.8759. Min Range: -2.8759

Max Act: 1.9599. Min Act: -0.0000

Data Index: 32223 (C4 (Web Text))

Max Activating Token Index: 568