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

Dataset: The Pile

Neuron 3165 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8680. Min Act: -0.0000

Data Index: 872135 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7980. Min Act: -0.0000

Data Index: 563708 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8527. Min Act: -0.0000

Data Index: 186131 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1827980 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5989. Min Act: -0.0000

Data Index: 44283 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1782087 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5949. Min Act: -0.0000

Data Index: 792453 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5595. Min Act: -0.0000

Data Index: 511323 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5389. Min Act: -0.0001

Data Index: 1637255 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1406461 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5776. Min Act: -0.0000

Data Index: 817489 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1214789 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.4966. Min Act: -0.0000

Data Index: 966025 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1347399 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5311. Min Act: -0.0000

Data Index: 476000 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1538447 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5107. Min Act: -0.0000

Data Index: 504433 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5009. Min Act: -0.0000

Data Index: 538560 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1155313 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.5436. Min Act: -0.0000

Data Index: 531603 (The Pile)

Max Activating Token Index: 573