Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4456 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4451. Min Range: -3.4451

Max Act: 3.4451. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 3.4451. Min Range: -3.4451

Max Act: 3.0835. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 3.4451. Min Range: -3.4451

Max Act: 2.4653. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 3.4451. Min Range: -3.4451

Max Act: 2.1018. Min Act: -0.0001

Data Index: 421681 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.9995. Min Act: -0.0000

Data Index: 1041224 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.4451. Min Range: -3.4451

Max Act: 2.0361. Min Act: -0.0001

Data Index: 296620 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.8215. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.8434. Min Act: -0.0001

Data Index: 372174 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.6470. Min Act: -0.0001

Data Index: 850366 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.7985. Min Act: -0.0001

Data Index: 683505 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.9634. Min Act: -0.0001

Data Index: 1211475 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.8117. Min Act: -0.0001

Data Index: 980987 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.7968. Min Act: -0.0001

Data Index: 1309674 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.7909. Min Act: -0.0001

Data Index: 973445 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.7413. Min Act: -0.0001

Data Index: 250542 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.7061. Min Act: -0.0001

Data Index: 717847 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.6587. Min Act: -0.0001

Data Index: 625109 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.7698. Min Act: -0.0001

Data Index: 438515 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.6803. Min Act: -0.0001

Data Index: 1609485 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 3.4451. Min Range: -3.4451

Max Act: 1.8407. Min Act: -0.0001

Data Index: 965947 (C4 (Web Text))

Max Activating Token Index: 815