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

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

Neuron 1199 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.4128. Min Act: -0.0001

Data Index: 230605 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3517. Min Act: -0.0002

Data Index: 419550 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.4414. Min Act: -0.0001

Data Index: 648841 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3267. Min Act: -0.0001

Data Index: 1252251 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2490. Min Act: -0.0001

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.3172. Min Act: -0.0002

Data Index: 945607 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2294. Min Act: -0.0002

Data Index: 605012 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2866. Min Act: -0.0002

Data Index: 413892 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2470. Min Act: -0.0002

Data Index: 324519 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0817. Min Act: -0.0001

Data Index: 1340170 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1789. Min Act: -0.0002

Data Index: 249590 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1263. Min Act: -0.0001

Data Index: 437285 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2533. Min Act: -0.0002

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2078. Min Act: -0.0001

Data Index: 1329394 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.0631. Min Act: -0.0002

Data Index: 1048031 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1138. Min Act: -0.0002

Data Index: 1068868 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1735. Min Act: -0.0001

Data Index: 267944 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1995. Min Act: -0.0001

Data Index: 1010075 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.1258. Min Act: -0.0001

Data Index: 971190 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.4414. Min Range: -1.4414

Max Act: 1.2816. Min Act: -0.0001

Data Index: 60913 (C4 (Web Text))

Max Activating Token Index: 611