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

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

Neuron 4529 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: 0.9184. Min Range: -0.9184

Max Act: 0.8988. Min Act: -0.0003

Data Index: 141618 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.9184. Min Act: -0.0002

Data Index: 451545 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8940. Min Act: -0.0002

Data Index: 180012 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8966. Min Act: -0.0002

Data Index: 514872 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8836. Min Act: -0.0002

Data Index: 896869 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8821. Min Act: -0.0002

Data Index: 816427 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8878. Min Act: -0.0002

Data Index: 211494 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8694. Min Act: -0.0002

Data Index: 1310540 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8664. Min Act: -0.0002

Data Index: 1098572 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8597. Min Act: -0.0002

Data Index: 1277248 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8504. Min Act: -0.0002

Data Index: 266087 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8669. Min Act: -0.0002

Data Index: 1358103 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8480. Min Act: -0.0002

Data Index: 587259 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8383. Min Act: -0.0003

Data Index: 1288945 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8400. Min Act: -0.0002

Data Index: 825682 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8248. Min Act: -0.0002

Data Index: 985094 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8284. Min Act: -0.0002

Data Index: 598834 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8192. Min Act: -0.0002

Data Index: 920638 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8085. Min Act: -0.0002

Data Index: 144616 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8357. Min Act: -0.0003

Data Index: 171412 (C4 (Web Text))

Max Activating Token Index: 131