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

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

Neuron 3274 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.9378. Min Act: -0.0000

Data Index: 906685 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.8448. Min Act: -0.0001

Data Index: 731649 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.8109. Min Act: -0.0000

Data Index: 630752 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.8005. Min Act: -0.0000

Data Index: 556172 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7963. Min Act: -0.0000

Data Index: 964813 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7955. Min Act: -0.0001

Data Index: 980777 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7710. Min Act: -0.0000

Data Index: 903585 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7300. Min Act: -0.0001

Data Index: 387099 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7573. Min Act: -0.0001

Data Index: 782868 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7443. Min Act: -0.0000

Data Index: 10653 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7322. Min Act: -0.0001

Data Index: 25878 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6923. Min Act: -0.0001

Data Index: 708125 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7350. Min Act: -0.0000

Data Index: 598980 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.7162. Min Act: -0.0000

Data Index: 578282 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1349532 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6558. Min Act: -0.0000

Data Index: 648187 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6669. Min Act: -0.0000

Data Index: 308987 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6600. Min Act: -0.0000

Data Index: 144628 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6755. Min Act: -0.0000

Data Index: 17218 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.9378. Min Range: -0.9378

Max Act: 0.6800. Min Act: -0.0000

Data Index: 190079 (C4 (Web Text))

Max Activating Token Index: 1007