Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9653. Min Act: -0.0000

Data Index: 1655803 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9194. Min Act: -0.0000

Data Index: 258427 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8385. Min Act: -0.0000

Data Index: 1965670 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.7747. Min Act: -0.0000

Data Index: 948637 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1659802 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.7070. Min Act: -0.0000

Data Index: 368226 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1984435 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5576. Min Act: -0.0000

Data Index: 841308 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1117827 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1691172 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.6450. Min Act: -0.0000

Data Index: 136744 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1606630 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.7192. Min Act: -0.0000

Data Index: 227281 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1989558 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1597556 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.7207. Min Act: -0.0000

Data Index: 145888 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5237. Min Act: -0.0000

Data Index: 1716694 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5619. Min Act: -0.0000

Data Index: 118669 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1034337 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1800442 (The Pile)

Max Activating Token Index: 101