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

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

Neuron 1649 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.5786. Min Act: -0.0000

Data Index: 722379 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.2872. Min Act: -0.0000

Data Index: 949210 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.2001. Min Act: -0.0000

Data Index: 768458 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 4.5786. Min Range: -4.5786

Max Act: 4.0230. Min Act: -0.0000

Data Index: 136532 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.9888. Min Act: -0.0000

Data Index: 487088 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.7361. Min Act: -0.0000

Data Index: 75325 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.9159. Min Act: -0.0000

Data Index: 924547 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.9567. Min Act: -0.0000

Data Index: 1101001 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.6780. Min Act: -0.0000

Data Index: 172271 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.8746. Min Act: -0.0000

Data Index: 639101 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.5260. Min Act: -0.0000

Data Index: 666893 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.5322. Min Act: -0.0000

Data Index: 627507 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.7479. Min Act: -0.0000

Data Index: 940725 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.7241. Min Act: -0.0000

Data Index: 1180933 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.6870. Min Act: -0.0000

Data Index: 1159868 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.3909. Min Act: -0.0000

Data Index: 39282 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.9892. Min Act: -0.0000

Data Index: 262543 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.4849. Min Act: -0.0000

Data Index: 634032 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.6472. Min Act: -0.0000

Data Index: 76703 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 4.5786. Min Range: -4.5786

Max Act: 3.3489. Min Act: -0.0000

Data Index: 265626 (C4 (Web Text))

Max Activating Token Index: 881