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

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

Neuron 3389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2431. Min Act: -0.0000

Data Index: 889292 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2189. Min Act: -0.0001

Data Index: 916436 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2288. Min Act: -0.0001

Data Index: 77847 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2170. Min Act: -0.0000

Data Index: 438581 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2083. Min Act: -0.0000

Data Index: 678205 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2011. Min Act: -0.0001

Data Index: 421604 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2078. Min Act: -0.0000

Data Index: 481360 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2041. Min Act: -0.0001

Data Index: 274236 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1909. Min Act: -0.0001

Data Index: 281881 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1947. Min Act: -0.0001

Data Index: 269640 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1925. Min Act: -0.0000

Data Index: 490225 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1981. Min Act: -0.0001

Data Index: 336040 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1803. Min Act: -0.0001

Data Index: 695366 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1793. Min Act: -0.0001

Data Index: 400945 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1734. Min Act: -0.0000

Data Index: 833916 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1723. Min Act: -0.0000

Data Index: 737360 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1723. Min Act: -0.0001

Data Index: 968518 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1083114 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1351822 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1042367 (C4 (Web Text))

Max Activating Token Index: 684