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

Dataset: The Pile

Neuron 1486 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1609597 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5810. Min Act: -0.0000

Data Index: 867424 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1151967 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4818. Min Act: -0.0000

Data Index: 758453 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5093. Min Act: -0.0000

Data Index: 420153 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4096. Min Act: -0.0000

Data Index: 608341 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4306. Min Act: -0.0000

Data Index: 517824 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4338. Min Act: -0.0000

Data Index: 997207 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1288154 (The Pile)

Max Activating Token Index: 180

Text #9

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4916. Min Act: -0.0000

Data Index: 757617 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4353. Min Act: -0.0000

Data Index: 451905 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4450. Min Act: -0.0000

Data Index: 323092 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4644. Min Act: -0.0000

Data Index: 74574 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1554015 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1913900 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1132963 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1323321 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1594316 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1573806 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.3638. Min Act: -0.0000

Data Index: 70559 (The Pile)

Max Activating Token Index: 676