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

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

Neuron 537 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5409. Min Range: -2.5409

Max Act: 2.5409. Min Act: -0.0000

Data Index: 15450 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 2.5409. Min Range: -2.5409

Max Act: 2.1923. Min Act: -0.0000

Data Index: 720002 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.9248. Min Act: -0.0000

Data Index: 450080 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.8237. Min Act: -0.0000

Data Index: 446435 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.7174. Min Act: -0.0000

Data Index: 313382 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.6751. Min Act: -0.0000

Data Index: 537116 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.6203. Min Act: -0.0000

Data Index: 404398 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.7446. Min Act: -0.0000

Data Index: 1119482 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.6000. Min Act: -0.0000

Data Index: 1026431 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.5689. Min Act: -0.0000

Data Index: 543876 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.5752. Min Act: -0.0000

Data Index: 1167975 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.5862. Min Act: -0.0000

Data Index: 508043 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.4323. Min Act: -0.0000

Data Index: 691857 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.4666. Min Act: -0.0000

Data Index: 730884 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.4616. Min Act: -0.0000

Data Index: 891578 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.4081. Min Act: -0.0000

Data Index: 521105 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.5278. Min Act: -0.0000

Data Index: 281644 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.3743. Min Act: -0.0000

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1037020 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 2.5409. Min Range: -2.5409

Max Act: 1.3609. Min Act: -0.0000

Data Index: 597629 (C4 (Web Text))

Max Activating Token Index: 226