Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.9510. Min Act: -0.0002

Data Index: 1243290 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.9189. Min Act: -0.0002

Data Index: 264576 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.9301. Min Act: -0.0002

Data Index: 207919 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8697. Min Act: -0.0002

Data Index: 1046257 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8417. Min Act: -0.0002

Data Index: 246147 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8503. Min Act: -0.0002

Data Index: 362011 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8373. Min Act: -0.0002

Data Index: 815184 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8276. Min Act: -0.0003

Data Index: 463053 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8363. Min Act: -0.0002

Data Index: 753904 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8275. Min Act: -0.0002

Data Index: 476574 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8125. Min Act: -0.0003

Data Index: 83884 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8250. Min Act: -0.0002

Data Index: 989270 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8231. Min Act: -0.0002

Data Index: 914341 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8105. Min Act: -0.0003

Data Index: 1304993 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8153. Min Act: -0.0002

Data Index: 295496 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8196. Min Act: -0.0002

Data Index: 835988 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.7923. Min Act: -0.0003

Data Index: 1082197 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.7975. Min Act: -0.0002

Data Index: 475551 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.8138. Min Act: -0.0002

Data Index: 885846 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.9510. Min Range: -0.9510

Max Act: 0.7977. Min Act: -0.0002

Data Index: 129298 (C4 (Web Text))

Max Activating Token Index: 649