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

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

Neuron 2870 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: 4.6785. Min Range: -4.6785

Max Act: 4.6785. Min Act: -0.0000

Data Index: 1280986 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 4.6785. Min Range: -4.6785

Max Act: 4.2378. Min Act: -0.0000

Data Index: 119343 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 4.6785. Min Range: -4.6785

Max Act: 4.3652. Min Act: -0.0000

Data Index: 1087961 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.7697. Min Act: -0.0000

Data Index: 582196 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 4.6785. Min Range: -4.6785

Max Act: 4.0486. Min Act: -0.0000

Data Index: 1015507 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 4.6785. Min Range: -4.6785

Max Act: 4.0441. Min Act: -0.0000

Data Index: 873628 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 4.6785. Min Range: -4.6785

Max Act: 4.0448. Min Act: -0.0000

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 4.6785. Min Range: -4.6785

Max Act: 4.1354. Min Act: -0.0000

Data Index: 105177 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.8974. Min Act: -0.0000

Data Index: 741859 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.8438. Min Act: -0.0000

Data Index: 394148 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.6707. Min Act: -0.0000

Data Index: 669536 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.6154. Min Act: -0.0000

Data Index: 1264460 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.4408. Min Act: -0.0000

Data Index: 539543 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.4995. Min Act: -0.0000

Data Index: 1145527 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.4728. Min Act: -0.0000

Data Index: 897996 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.4265. Min Act: -0.0000

Data Index: 9923 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.6237. Min Act: -0.0000

Data Index: 1296996 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.5717. Min Act: -0.0000

Data Index: 1165995 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.5359. Min Act: -0.0000

Data Index: 247502 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 4.6785. Min Range: -4.6785

Max Act: 3.4930. Min Act: -0.0000

Data Index: 135409 (C4 (Web Text))

Max Activating Token Index: 880