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

Dataset: The Pile

Neuron 3794 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: 3.2624. Min Range: -3.2624

Max Act: 3.2624. Min Act: -0.0000

Data Index: 372346 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 3.2624. Min Range: -3.2624

Max Act: 3.0161. Min Act: -0.0000

Data Index: 1637655 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.9830. Min Act: -0.0000

Data Index: 258473 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.8906. Min Act: -0.0000

Data Index: 1111133 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 3.2624. Min Range: -3.2624

Max Act: 3.0234. Min Act: -0.0000

Data Index: 1490374 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.7997. Min Act: -0.0000

Data Index: 109944 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.6495. Min Act: -0.0000

Data Index: 436241 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.7748. Min Act: -0.0000

Data Index: 1935310 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.5960. Min Act: -0.0000

Data Index: 402999 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.5918. Min Act: -0.0000

Data Index: 1797989 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.7967. Min Act: -0.0000

Data Index: 339542 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.5416. Min Act: -0.0000

Data Index: 374207 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.6268. Min Act: -0.0000

Data Index: 609011 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.6102. Min Act: -0.0000

Data Index: 975482 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.5983. Min Act: -0.0000

Data Index: 1198351 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.4397. Min Act: -0.0000

Data Index: 571918 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 3.2624. Min Range: -3.2624

Max Act: 3.0001. Min Act: -0.0000

Data Index: 1763311 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.5150. Min Act: -0.0000

Data Index: 1052310 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.3568. Min Act: -0.0000

Data Index: 500670 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 3.2624. Min Range: -3.2624

Max Act: 2.3194. Min Act: -0.0000

Data Index: 885464 (The Pile)

Max Activating Token Index: 560