Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1853 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1930. Min Range: -1.1930

Max Act: 1.1930. Min Act: -0.0001

Data Index: 1175819 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.8311. Min Act: -0.0001

Data Index: 156291 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.7272. Min Act: -0.0001

Data Index: 798193 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6663. Min Act: -0.0001

Data Index: 28868 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.7569. Min Act: -0.0001

Data Index: 1210586 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.7436. Min Act: -0.0001

Data Index: 851128 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.7053. Min Act: -0.0001

Data Index: 896998 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6384. Min Act: -0.0001

Data Index: 4196 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6426. Min Act: -0.0001

Data Index: 392314 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6839. Min Act: -0.0001

Data Index: 194425 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6111. Min Act: -0.0001

Data Index: 373127 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6455. Min Act: -0.0001

Data Index: 910428 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1498667 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6389. Min Act: -0.0001

Data Index: 1344620 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6084. Min Act: -0.0001

Data Index: 1440155 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.5890. Min Act: -0.0001

Data Index: 727119 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.5903. Min Act: -0.0001

Data Index: 1472349 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.5581. Min Act: -0.0001

Data Index: 1415616 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6448. Min Act: -0.0001

Data Index: 828431 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.1930. Min Range: -1.1930

Max Act: 0.6208. Min Act: -0.0001

Data Index: 1503686 (Python Code)

Max Activating Token Index: 49