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

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

Neuron 775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.7461. Min Act: -0.0000

Data Index: 79826 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.8427. Min Act: -0.0000

Data Index: 339409 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.5061. Min Act: -0.0001

Data Index: 717868 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.3355. Min Act: -0.0000

Data Index: 107620 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.5190. Min Act: -0.0001

Data Index: 1046475 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.2917. Min Act: -0.0001

Data Index: 1329005 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1566. Min Act: -0.0000

Data Index: 224446 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.2307. Min Act: -0.0000

Data Index: 414416 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.0475. Min Act: -0.0001

Data Index: 999203 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.0281. Min Act: -0.0000

Data Index: 871477 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1442. Min Act: -0.0001

Data Index: 1331891 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.8427. Min Range: -3.8427

Max Act: 2.9970. Min Act: -0.0001

Data Index: 1320069 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 3.8427. Min Range: -3.8427

Max Act: 2.7302. Min Act: -0.0001

Data Index: 1152277 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1229. Min Act: -0.0001

Data Index: 517226 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.2760. Min Act: -0.0001

Data Index: 21476 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.0506. Min Act: -0.0000

Data Index: 951073 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.0684. Min Act: -0.0001

Data Index: 846450 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.0552. Min Act: -0.0001

Data Index: 229221 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1770. Min Act: -0.0000

Data Index: 334680 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.8427. Min Range: -3.8427

Max Act: 2.9903. Min Act: -0.0001

Data Index: 1244822 (C4 (Web Text))

Max Activating Token Index: 896