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

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

Neuron 5 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3591. Min Range: -2.3591

Max Act: 2.3591. Min Act: -0.0000

Data Index: 592795 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 2.3591. Min Range: -2.3591

Max Act: 2.1356. Min Act: -0.0001

Data Index: 54075 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 2.3591. Min Range: -2.3591

Max Act: 2.0936. Min Act: -0.0000

Data Index: 163764 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.9278. Min Act: -0.0000

Data Index: 109300 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7879. Min Act: -0.0000

Data Index: 42968 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6634. Min Act: -0.0000

Data Index: 437955 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7394. Min Act: -0.0000

Data Index: 880752 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1221154 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.7873. Min Act: -0.0001

Data Index: 546999 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.5887. Min Act: -0.0000

Data Index: 710004 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6483. Min Act: -0.0000

Data Index: 750796 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6276. Min Act: -0.0000

Data Index: 857315 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1015047 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.5264. Min Act: -0.0001

Data Index: 242772 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6065. Min Act: -0.0000

Data Index: 63429 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.5767. Min Act: -0.0000

Data Index: 334695 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.5755. Min Act: -0.0000

Data Index: 395377 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.5650. Min Act: -0.0000

Data Index: 1150672 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6234. Min Act: -0.0000

Data Index: 458284 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 2.3591. Min Range: -2.3591

Max Act: 1.6914. Min Act: -0.0001

Data Index: 1088532 (C4 (Web Text))

Max Activating Token Index: 808