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

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

Neuron 1415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.8083. Min Act: -0.0000

Data Index: 111354 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.7793. Min Act: -0.0000

Data Index: 781331 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.5964. Min Act: -0.0000

Data Index: 332451 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.2815. Min Act: -0.0000

Data Index: 286192 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.3262. Min Act: -0.0000

Data Index: 156353 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.2381. Min Act: -0.0000

Data Index: 1196665 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.4478. Min Act: -0.0000

Data Index: 1110305 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.3828. Min Act: -0.0001

Data Index: 259225 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.3372. Min Act: -0.0000

Data Index: 3954 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1145. Min Act: -0.0000

Data Index: 915427 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1877. Min Act: -0.0000

Data Index: 1003329 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1878. Min Act: -0.0000

Data Index: 239794 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1479. Min Act: -0.0000

Data Index: 299059 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1370. Min Act: -0.0000

Data Index: 196725 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.2390. Min Act: -0.0000

Data Index: 486528 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 2.8083. Min Range: -2.8083

Max Act: 1.9946. Min Act: -0.0000

Data Index: 847034 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.3079. Min Act: -0.0000

Data Index: 885794 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.2754. Min Act: -0.0000

Data Index: 101935 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1527. Min Act: -0.0000

Data Index: 1195363 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 2.8083. Min Range: -2.8083

Max Act: 2.1488. Min Act: -0.0000

Data Index: 763983 (C4 (Web Text))

Max Activating Token Index: 524