Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3373 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0053. Min Range: -1.0053

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1635732 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1791836 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1728600 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7105. Min Act: -0.0000

Data Index: 955124 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7226. Min Act: -0.0000

Data Index: 467925 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.7343. Min Act: -0.0000

Data Index: 555344 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1124731 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6529. Min Act: -0.0000

Data Index: 653033 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6413. Min Act: -0.0000

Data Index: 445963 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6117. Min Act: -0.0000

Data Index: 752212 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6318. Min Act: -0.0000

Data Index: 985898 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1442460 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1182640 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1391848 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1651213 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1368407 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1231716 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.4867. Min Act: -0.0000

Data Index: 653264 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.5360. Min Act: -0.0000

Data Index: 732311 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 1.0053. Min Range: -1.0053

Max Act: 0.4704. Min Act: -0.0000

Data Index: 290130 (The Pile)

Max Activating Token Index: 547