Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 461 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1121400 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3908. Min Act: -0.0000

Data Index: 233352 (The Pile)

Max Activating Token Index: 667

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1267898 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3788. Min Act: -0.0000

Data Index: 546240 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3583. Min Act: -0.0000

Data Index: 697310 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3486. Min Act: -0.0000

Data Index: 60133 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3111. Min Act: -0.0000

Data Index: 889023 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1800886 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1777558 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3251. Min Act: -0.0000

Data Index: 9305 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1965643 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2959. Min Act: -0.0000

Data Index: 319060 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3061. Min Act: -0.0000

Data Index: 486132 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3021. Min Act: -0.0000

Data Index: 438476 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1296305 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2905. Min Act: -0.0000

Data Index: 573090 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1400983 (The Pile)

Max Activating Token Index: 796

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2837. Min Act: 0.0000

Data Index: 1456308 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1826119 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2888. Min Act: -0.0000

Data Index: 597686 (The Pile)

Max Activating Token Index: 92