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

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

Neuron 2364 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: 0.5372. Min Range: -0.5372

Max Act: 0.5372. Min Act: -0.0002

Data Index: 707221 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4188. Min Act: -0.0001

Data Index: 176731 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4076. Min Act: -0.0001

Data Index: 12088 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4443. Min Act: -0.0002

Data Index: 1179779 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4517. Min Act: -0.0002

Data Index: 402849 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4550. Min Act: -0.0001

Data Index: 34513 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4279. Min Act: -0.0002

Data Index: 851185 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4274. Min Act: -0.0002

Data Index: 998926 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1191437 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3995. Min Act: -0.0002

Data Index: 59996 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4209. Min Act: -0.0002

Data Index: 137162 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4117. Min Act: -0.0002

Data Index: 1037028 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4377. Min Act: -0.0001

Data Index: 45859 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4353. Min Act: -0.0002

Data Index: 813065 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1379754 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4125. Min Act: -0.0002

Data Index: 444557 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3980. Min Act: -0.0002

Data Index: 26310 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4122. Min Act: -0.0001

Data Index: 846794 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4089. Min Act: -0.0001

Data Index: 120947 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3388. Min Act: -0.0001

Data Index: 757343 (C4 (Web Text))

Max Activating Token Index: 401