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

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

Neuron 3568 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.3056. Min Act: -0.0000

Data Index: 926213 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1156304 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2851. Min Act: -0.0000

Data Index: 929537 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1182113 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2830. Min Act: -0.0001

Data Index: 590001 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2751. Min Act: -0.0001

Data Index: 83694 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2635. Min Act: -0.0000

Data Index: 474384 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2622. Min Act: 0.0000

Data Index: 1170892 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1239370 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2507. Min Act: -0.0001

Data Index: 49379 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1015750 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2575. Min Act: 0.0000

Data Index: 590692 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2404. Min Act: 0.0000

Data Index: 1274722 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2727. Min Act: -0.0000

Data Index: 107297 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2469. Min Act: -0.0000

Data Index: 452848 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2512. Min Act: -0.0000

Data Index: 624 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2627. Min Act: -0.0000

Data Index: 225145 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2367. Min Act: -0.0000

Data Index: 965110 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2420. Min Act: -0.0001

Data Index: 539046 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.3056. Min Range: -0.3056

Max Act: 0.2463. Min Act: -0.0000

Data Index: 641225 (C4 (Web Text))

Max Activating Token Index: 901