Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.5150. Min Act: -0.0000

Data Index: 998609 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4610. Min Act: -0.0000

Data Index: 797701 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3650. Min Act: -0.0000

Data Index: 554046 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3625. Min Act: -0.0000

Data Index: 568677 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2807. Min Act: -0.0000

Data Index: 254320 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1344937 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3193. Min Act: -0.0000

Data Index: 401819 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3084. Min Act: -0.0000

Data Index: 859799 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2914. Min Act: -0.0000

Data Index: 669263 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2820. Min Act: -0.0000

Data Index: 209302 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2905. Min Act: -0.0000

Data Index: 96672 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2924. Min Act: -0.0000

Data Index: 690763 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2910. Min Act: -0.0000

Data Index: 341919 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2492. Min Act: -0.0000

Data Index: 923724 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2664. Min Act: -0.0000

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.1585. Min Act: -0.0000

Data Index: 389615 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1182305 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2388. Min Act: -0.0000

Data Index: 616097 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1325110 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2225. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 233