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

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

Neuron 137 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: 0.9932. Min Range: -0.9932

Max Act: 0.9932. Min Act: 0.0000

Data Index: 360817 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1322343 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9019. Min Act: -0.0000

Data Index: 757843 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8737. Min Act: -0.0000

Data Index: 694762 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8186. Min Act: -0.0000

Data Index: 763598 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8429. Min Act: -0.0000

Data Index: 798222 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7940. Min Act: -0.0000

Data Index: 393535 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7814. Min Act: -0.0000

Data Index: 906997 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1336859 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7673. Min Act: -0.0000

Data Index: 486933 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7533. Min Act: -0.0000

Data Index: 736498 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7729. Min Act: -0.0000

Data Index: 85531 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7494. Min Act: -0.0000

Data Index: 620023 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7182. Min Act: -0.0000

Data Index: 350745 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7581. Min Act: -0.0000

Data Index: 771201 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7439. Min Act: -0.0000

Data Index: 600485 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7126. Min Act: -0.0000

Data Index: 994484 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7687. Min Act: -0.0000

Data Index: 458527 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7295. Min Act: -0.0000

Data Index: 520272 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7221. Min Act: -0.0000

Data Index: 316019 (C4 (Web Text))

Max Activating Token Index: 786