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

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

Neuron 1731 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2318. Min Range: -8.2318

Max Act: 8.2318. Min Act: -0.0000

Data Index: 22865 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 8.2318. Min Range: -8.2318

Max Act: 7.6068. Min Act: -0.0000

Data Index: 1500864 (Python Code)

Max Activating Token Index: 755

Text #2

Max Range: 8.2318. Min Range: -8.2318

Max Act: 7.9361. Min Act: -0.0001

Data Index: 1621218 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 8.2318. Min Range: -8.2318

Max Act: 7.2346. Min Act: -0.0001

Data Index: 1580503 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 8.2318. Min Range: -8.2318

Max Act: 6.8426. Min Act: -0.0000

Data Index: 1339760 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 8.2318. Min Range: -8.2318

Max Act: 6.6789. Min Act: -0.0001

Data Index: 1298491 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 8.2318. Min Range: -8.2318

Max Act: 6.8365. Min Act: -0.0000

Data Index: 1311155 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 8.2318. Min Range: -8.2318

Max Act: 6.6584. Min Act: -0.0000

Data Index: 82650 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.8393. Min Act: -0.0000

Data Index: 493262 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 8.2318. Min Range: -8.2318

Max Act: 6.0740. Min Act: -0.0001

Data Index: 933457 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.9842. Min Act: -0.0000

Data Index: 895159 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.3803. Min Act: -0.0000

Data Index: 330200 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.3685. Min Act: -0.0000

Data Index: 1023506 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.6959. Min Act: -0.0000

Data Index: 438827 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.3933. Min Act: -0.0000

Data Index: 999471 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.0028. Min Act: -0.0001

Data Index: 1359402 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.1667. Min Act: -0.0000

Data Index: 342765 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 8.2318. Min Range: -8.2318

Max Act: 4.9608. Min Act: -0.0000

Data Index: 1106709 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.2716. Min Act: -0.0001

Data Index: 825405 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 8.2318. Min Range: -8.2318

Max Act: 5.0723. Min Act: -0.0000

Data Index: 524047 (C4 (Web Text))

Max Activating Token Index: 579