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

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

Neuron 893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3687. Min Act: -0.0002

Data Index: 1166464 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3741. Min Act: -0.0001

Data Index: 184833 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3199. Min Act: -0.0001

Data Index: 840362 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3011. Min Act: -0.0001

Data Index: 1216979 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2600. Min Act: -0.0001

Data Index: 1010823 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2566. Min Act: -0.0002

Data Index: 438921 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2473. Min Act: -0.0002

Data Index: 419631 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2067. Min Act: -0.0001

Data Index: 1229931 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2405. Min Act: -0.0002

Data Index: 251987 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2018. Min Act: -0.0001

Data Index: 1298998 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1970. Min Act: -0.0001

Data Index: 58199 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2505. Min Act: -0.0002

Data Index: 1144749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.1811. Min Act: -0.0001

Data Index: 132880 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2165. Min Act: -0.0001

Data Index: 1183904 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2808. Min Act: -0.0001

Data Index: 273423 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.3481. Min Act: -0.0001

Data Index: 747811 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2446. Min Act: -0.0002

Data Index: 121542 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2443. Min Act: -0.0001

Data Index: 1201057 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2071. Min Act: -0.0001

Data Index: 928311 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.3741. Min Range: -1.3741

Max Act: 1.2414. Min Act: -0.0002

Data Index: 884783 (C4 (Web Text))

Max Activating Token Index: 21