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

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

Neuron 2999 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: 0.3903. Min Range: -0.3903

Max Act: 0.3903. Min Act: -0.0001

Data Index: 1240152 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1137778 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2488. Min Act: -0.0001

Data Index: 979716 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1164785 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2415. Min Act: -0.0001

Data Index: 62553 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2456. Min Act: -0.0001

Data Index: 766086 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2539. Min Act: -0.0001

Data Index: 324746 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2279. Min Act: -0.0001

Data Index: 105643 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1213994 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2319. Min Act: -0.0001

Data Index: 131932 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2198. Min Act: -0.0001

Data Index: 930442 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1251947 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2092. Min Act: -0.0001

Data Index: 250608 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.1933. Min Act: -0.0001

Data Index: 628077 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2120. Min Act: -0.0001

Data Index: 10448 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2186. Min Act: -0.0001

Data Index: 200093 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2106. Min Act: -0.0001

Data Index: 437990 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2102. Min Act: -0.0001

Data Index: 835492 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1221508 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.3903. Min Range: -0.3903

Max Act: 0.1785. Min Act: -0.0001

Data Index: 629041 (C4 (Web Text))

Max Activating Token Index: 13