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

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

Neuron 1164 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.7761. Min Act: -0.0000

Data Index: 62231 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.6003. Min Act: -0.0000

Data Index: 874707 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1424674 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5664. Min Act: 0.0000

Data Index: 767988 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1101401 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5038. Min Act: -0.0000

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1106410 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1160454 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5211. Min Act: -0.0000

Data Index: 513005 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1206851 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4881. Min Act: 0.0000

Data Index: 973419 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4703. Min Act: -0.0000

Data Index: 666149 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4539. Min Act: -0.0000

Data Index: 510472 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4383. Min Act: -0.0000

Data Index: 114904 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4585. Min Act: -0.0000

Data Index: 595913 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1530409 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4359. Min Act: -0.0000

Data Index: 818515 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.4167. Min Act: -0.0000

Data Index: 709690 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.3948. Min Act: -0.0000

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 875