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

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

Neuron 2793 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0860. Min Act: -0.0000

Data Index: 136142 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1596. Min Act: -0.0000

Data Index: 208705 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9031. Min Act: -0.0000

Data Index: 852112 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9497. Min Act: -0.0000

Data Index: 496374 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.0330. Min Act: -0.0000

Data Index: 126777 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8779. Min Act: -0.0000

Data Index: 777530 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9265. Min Act: -0.0000

Data Index: 675357 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8654. Min Act: -0.0000

Data Index: 72169 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8524. Min Act: -0.0000

Data Index: 902734 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1057972 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8582. Min Act: -0.0000

Data Index: 480182 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1271803 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7731. Min Act: -0.0000

Data Index: 442866 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7900. Min Act: -0.0000

Data Index: 880821 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8385. Min Act: -0.0000

Data Index: 887178 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7439. Min Act: -0.0000

Data Index: 365756 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1348966 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1248032 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1629411 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7516. Min Act: -0.0000

Data Index: 17125 (C4 (Web Text))

Max Activating Token Index: 565