Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2683 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1262037 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.8223. Min Act: -0.0000

Data Index: 926483 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6755. Min Act: -0.0000

Data Index: 591322 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6368. Min Act: -0.0000

Data Index: 95765 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6363. Min Act: -0.0000

Data Index: 504422 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5628. Min Act: -0.0000

Data Index: 312223 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5747. Min Act: -0.0000

Data Index: 762992 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5364. Min Act: -0.0000

Data Index: 878486 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5192. Min Act: -0.0000

Data Index: 446195 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1248390 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4903. Min Act: -0.0000

Data Index: 313150 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5667. Min Act: -0.0000

Data Index: 520726 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5177. Min Act: -0.0000

Data Index: 546356 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1140928 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4947. Min Act: -0.0000

Data Index: 126219 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5108. Min Act: -0.0000

Data Index: 831262 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4455. Min Act: -0.0000

Data Index: 856932 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4726. Min Act: -0.0000

Data Index: 477800 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4876. Min Act: -0.0000

Data Index: 394498 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1330354 (C4 (Web Text))

Max Activating Token Index: 520