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

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

Neuron 4736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0371. Min Range: -1.0371

Max Act: 1.0371. Min Act: -0.0000

Data Index: 213155 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.0371. Min Range: -1.0371

Max Act: 1.0015. Min Act: -0.0000

Data Index: 501303 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.9681. Min Act: -0.0000

Data Index: 750440 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.0371. Min Range: -1.0371

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1343493 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8461. Min Act: -0.0000

Data Index: 941634 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8712. Min Act: -0.0000

Data Index: 202697 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8923. Min Act: -0.0000

Data Index: 604044 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7952. Min Act: -0.0000

Data Index: 820986 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1239028 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8063. Min Act: -0.0000

Data Index: 963805 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8026. Min Act: -0.0000

Data Index: 246864 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.8303. Min Act: -0.0000

Data Index: 839486 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7829. Min Act: -0.0000

Data Index: 948653 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7992. Min Act: -0.0000

Data Index: 779762 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7742. Min Act: -0.0000

Data Index: 705864 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1064311 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7685. Min Act: -0.0000

Data Index: 501507 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7600. Min Act: -0.0000

Data Index: 833287 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7341. Min Act: -0.0000

Data Index: 560259 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.0371. Min Range: -1.0371

Max Act: 0.7719. Min Act: -0.0000

Data Index: 419082 (C4 (Web Text))

Max Activating Token Index: 954