Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2575 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3763. Min Act: -0.0000

Data Index: 179148 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3576. Min Act: -0.0000

Data Index: 88653 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1073297 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3410. Min Act: -0.0000

Data Index: 52463 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3493. Min Act: -0.0000

Data Index: 982956 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1478304 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1450468 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3230. Min Act: -0.0000

Data Index: 628228 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3240. Min Act: -0.0000

Data Index: 305963 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2732. Min Act: -0.0000

Data Index: 243287 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1451619 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1164479 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1629227 (Python Code)

Max Activating Token Index: 861

Text #13

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1508126 (Python Code)

Max Activating Token Index: 749

Text #14

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1480517 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3082. Min Act: -0.0000

Data Index: 498743 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3224. Min Act: -0.0000

Data Index: 81043 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3023. Min Act: -0.0000

Data Index: 84916 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3002. Min Act: -0.0000

Data Index: 513666 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1059192 (C4 (Web Text))

Max Activating Token Index: 324