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

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

Neuron 2070 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.6656. Min Act: -0.0001

Data Index: 169615 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5511. Min Act: -0.0001

Data Index: 1355974 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1179799 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5544. Min Act: -0.0001

Data Index: 473437 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5150. Min Act: -0.0001

Data Index: 271294 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5120. Min Act: -0.0001

Data Index: 68790 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4939. Min Act: -0.0001

Data Index: 518229 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5258. Min Act: -0.0001

Data Index: 1223576 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5142. Min Act: -0.0001

Data Index: 556860 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4902. Min Act: -0.0001

Data Index: 1242757 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4871. Min Act: -0.0001

Data Index: 925800 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4896. Min Act: -0.0001

Data Index: 891216 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4803. Min Act: -0.0001

Data Index: 606836 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4760. Min Act: -0.0001

Data Index: 397302 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4917. Min Act: -0.0001

Data Index: 1345031 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4824. Min Act: -0.0001

Data Index: 1030850 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4656. Min Act: -0.0001

Data Index: 570948 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4977. Min Act: -0.0001

Data Index: 830144 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4815. Min Act: -0.0001

Data Index: 669289 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4653. Min Act: -0.0001

Data Index: 1258407 (C4 (Web Text))

Max Activating Token Index: 25