Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2998 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0001

Data Index: 379541 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8913. Min Act: -0.0001

Data Index: 21986 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1172916 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8573. Min Act: -0.0001

Data Index: 756035 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8692. Min Act: -0.0001

Data Index: 565732 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8358. Min Act: -0.0001

Data Index: 295714 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8148. Min Act: -0.0001

Data Index: 1306464 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8270. Min Act: -0.0001

Data Index: 382052 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7694. Min Act: -0.0001

Data Index: 477092 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7685. Min Act: -0.0001

Data Index: 646396 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7787. Min Act: -0.0001

Data Index: 402668 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7803. Min Act: -0.0001

Data Index: 348635 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7453. Min Act: -0.0001

Data Index: 371755 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7330. Min Act: -0.0001

Data Index: 687614 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7264. Min Act: -0.0001

Data Index: 1155056 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7491. Min Act: -0.0001

Data Index: 736142 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5864. Min Act: -0.0001

Data Index: 291395 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7081. Min Act: -0.0001

Data Index: 1205363 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1032360 (C4 (Web Text))

Max Activating Token Index: 715