Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3729. Min Act: -0.0000

Data Index: 100878 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2573. Min Act: -0.0000

Data Index: 785646 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1343040 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1309. Min Act: -0.0000

Data Index: 810509 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1328. Min Act: -0.0000

Data Index: 335974 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1410. Min Act: -0.0001

Data Index: 147849 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1647. Min Act: -0.0000

Data Index: 558020 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1986. Min Act: -0.0001

Data Index: 202613 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0654. Min Act: -0.0000

Data Index: 956079 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9683. Min Act: -0.0001

Data Index: 79150 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0490. Min Act: -0.0000

Data Index: 478805 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9642. Min Act: -0.0001

Data Index: 267461 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0673. Min Act: -0.0001

Data Index: 791221 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1133. Min Act: -0.0001

Data Index: 1012247 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0585. Min Act: -0.0000

Data Index: 299533 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1086. Min Act: -0.0000

Data Index: 901429 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0751. Min Act: -0.0000

Data Index: 191774 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1244. Min Act: -0.0001

Data Index: 537292 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0729. Min Act: -0.0001

Data Index: 124189 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9627. Min Act: -0.0001

Data Index: 117780 (C4 (Web Text))

Max Activating Token Index: 669