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

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

Neuron 2293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1055947 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0001

Data Index: 347763 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0782. Min Act: -0.0001

Data Index: 748394 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0729. Min Act: -0.0001

Data Index: 154939 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0705. Min Act: -0.0001

Data Index: 955373 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0682. Min Act: -0.0001

Data Index: 684501 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0679. Min Act: -0.0001

Data Index: 401604 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1211987 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0643. Min Act: -0.0001

Data Index: 204128 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0630. Min Act: -0.0001

Data Index: 110014 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0648. Min Act: -0.0001

Data Index: 324114 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0646. Min Act: -0.0001

Data Index: 315132 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0625. Min Act: -0.0001

Data Index: 508 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0620. Min Act: -0.0001

Data Index: 101677 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0640. Min Act: -0.0001

Data Index: 606952 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1029412 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0599. Min Act: -0.0001

Data Index: 437390 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0596. Min Act: -0.0001

Data Index: 150357 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0574. Min Act: -0.0001

Data Index: 153327 (C4 (Web Text))

Max Activating Token Index: 115