Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 159 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5457. Min Act: -0.0001

Data Index: 247075 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5570. Min Act: -0.0001

Data Index: 507650 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4985. Min Act: -0.0001

Data Index: 1330210 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4873. Min Act: -0.0001

Data Index: 937164 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5001. Min Act: -0.0001

Data Index: 826413 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4670. Min Act: -0.0001

Data Index: 1356210 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4631. Min Act: -0.0001

Data Index: 504105 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4739. Min Act: -0.0001

Data Index: 886158 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4457. Min Act: -0.0001

Data Index: 213613 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4559. Min Act: -0.0001

Data Index: 905341 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1292378 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4593. Min Act: -0.0001

Data Index: 595060 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4599. Min Act: -0.0001

Data Index: 1200749 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4638. Min Act: -0.0001

Data Index: 414722 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4578. Min Act: -0.0001

Data Index: 976171 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1062786 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4797. Min Act: -0.0001

Data Index: 633584 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4740. Min Act: -0.0001

Data Index: 6418 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1102018 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4044. Min Act: -0.0001

Data Index: 51540 (C4 (Web Text))

Max Activating Token Index: 106