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

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

Neuron 4244 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0002

Data Index: 755647 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0753. Min Act: -0.0002

Data Index: 945054 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0690. Min Act: -0.0002

Data Index: 70008 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0647. Min Act: -0.0002

Data Index: 142022 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0593. Min Act: -0.0002

Data Index: 894119 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0589. Min Act: -0.0002

Data Index: 876333 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1186527 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1134183 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0550. Min Act: -0.0002

Data Index: 7492 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0542. Min Act: -0.0002

Data Index: 181990 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1171797 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0550. Min Act: -0.0002

Data Index: 5160 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1217833 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0541. Min Act: -0.0002

Data Index: 34384 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0533. Min Act: -0.0002

Data Index: 275350 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0518. Min Act: -0.0002

Data Index: 755538 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0518. Min Act: -0.0002

Data Index: 441281 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0544. Min Act: -0.0002

Data Index: 23070 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1255752 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0469. Min Act: -0.0002

Data Index: 473094 (C4 (Web Text))

Max Activating Token Index: 267