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

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

Neuron 3458 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: 0.6679. Min Range: -0.6679

Max Act: 0.6246. Min Act: -0.0001

Data Index: 1307777 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.6679. Min Act: -0.0000

Data Index: 512348 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.6444. Min Act: -0.0001

Data Index: 888631 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.6200. Min Act: -0.0001

Data Index: 822923 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5972. Min Act: -0.0000

Data Index: 603273 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5570. Min Act: -0.0000

Data Index: 287980 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5946. Min Act: -0.0001

Data Index: 61848 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5686. Min Act: -0.0001

Data Index: 1300986 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5644. Min Act: -0.0000

Data Index: 590073 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5451. Min Act: -0.0001

Data Index: 581128 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5438. Min Act: -0.0001

Data Index: 592855 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1135037 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1097134 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5864. Min Act: -0.0001

Data Index: 982 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5271. Min Act: -0.0001

Data Index: 916717 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5756. Min Act: -0.0001

Data Index: 808833 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1030230 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1327729 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5753. Min Act: -0.0001

Data Index: 922999 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.6679. Min Range: -0.6679

Max Act: 0.5875. Min Act: -0.0000

Data Index: 276742 (C4 (Web Text))

Max Activating Token Index: 991