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

Dataset: The Pile

Neuron 3532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6815. Min Act: -0.0000

Data Index: 356136 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1995108 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1254121 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1786057 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1663042 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1409931 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4645. Min Act: -0.0000

Data Index: 503758 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4760. Min Act: -0.0000

Data Index: 272111 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1734777 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4405. Min Act: 0.0000

Data Index: 680004 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4577. Min Act: 0.0000

Data Index: 1514591 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4466. Min Act: -0.0000

Data Index: 830535 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4357. Min Act: -0.0000

Data Index: 576790 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.3936. Min Act: -0.0000

Data Index: 254461 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1283196 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.3767. Min Act: -0.0000

Data Index: 487454 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.3962. Min Act: -0.0000

Data Index: 616656 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1285435 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.3785. Min Act: -0.0000

Data Index: 548454 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.3757. Min Act: -0.0000

Data Index: 817118 (The Pile)

Max Activating Token Index: 588