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

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

Neuron 5018 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: 0.9167. Min Range: -0.9167

Max Act: 0.9167. Min Act: 0.0001

Data Index: 706324 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1039150 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.7677. Min Act: -0.0000

Data Index: 750659 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6963. Min Act: 0.0000

Data Index: 461631 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6622. Min Act: -0.0000

Data Index: 932936 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6359. Min Act: 0.0000

Data Index: 122522 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.6098. Min Act: 0.0000

Data Index: 18211 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5715. Min Act: 0.0000

Data Index: 1174128 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5420. Min Act: -0.0000

Data Index: 893001 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1351906 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5276. Min Act: 0.0001

Data Index: 888957 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5425. Min Act: 0.0001

Data Index: 1245045 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5155. Min Act: 0.0000

Data Index: 819110 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.4863. Min Act: -0.0000

Data Index: 851884 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.4903. Min Act: 0.0000

Data Index: 284500 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5046. Min Act: 0.0000

Data Index: 1130236 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5141. Min Act: 0.0000

Data Index: 456407 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1591772 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.4950. Min Act: -0.0000

Data Index: 95212 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.9167. Min Range: -0.9167

Max Act: 0.4796. Min Act: 0.0001

Data Index: 806067 (C4 (Web Text))

Max Activating Token Index: 628