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

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

Neuron 2096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4515. Min Act: -0.0001

Data Index: 303661 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4228. Min Act: -0.0001

Data Index: 1222915 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4244. Min Act: -0.0000

Data Index: 481605 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4171. Min Act: -0.0000

Data Index: 597488 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4032. Min Act: -0.0000

Data Index: 318265 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4149. Min Act: -0.0001

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1199961 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4004. Min Act: -0.0000

Data Index: 987852 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4097. Min Act: -0.0000

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4082. Min Act: -0.0001

Data Index: 1082514 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3936. Min Act: -0.0000

Data Index: 264807 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1331633 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.4013. Min Act: -0.0000

Data Index: 899385 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3873. Min Act: -0.0000

Data Index: 514072 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3751. Min Act: -0.0000

Data Index: 288611 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3865. Min Act: -0.0000

Data Index: 652377 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3957. Min Act: -0.0001

Data Index: 497409 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3820. Min Act: -0.0000

Data Index: 837433 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1151910 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.4515. Min Range: -0.4515

Max Act: 0.3747. Min Act: -0.0000

Data Index: 480033 (C4 (Web Text))

Max Activating Token Index: 223