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

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

Neuron 3874 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3749. Min Act: -0.0000

Data Index: 636496 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3123. Min Act: -0.0000

Data Index: 442404 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2452. Min Act: -0.0001

Data Index: 751597 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1655. Min Act: -0.0001

Data Index: 123500 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1086532 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1232819 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1118. Min Act: -0.0001

Data Index: 1052770 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0633. Min Act: -0.0001

Data Index: 261450 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1057080 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9797. Min Act: -0.0000

Data Index: 40084 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1177132 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0277. Min Act: -0.0001

Data Index: 467087 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0489. Min Act: -0.0000

Data Index: 777884 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0776. Min Act: -0.0000

Data Index: 547120 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1057998 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0445. Min Act: -0.0000

Data Index: 413768 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0016. Min Act: -0.0001

Data Index: 304929 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9592. Min Act: -0.0000

Data Index: 774102 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9670. Min Act: -0.0001

Data Index: 1246092 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9739. Min Act: -0.0000

Data Index: 892244 (C4 (Web Text))

Max Activating Token Index: 118