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

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

Neuron 5398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.5262. Min Act: -0.0001

Data Index: 983003 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.5030. Min Act: -0.0001

Data Index: 839116 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4669. Min Act: -0.0001

Data Index: 2860 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4918. Min Act: -0.0001

Data Index: 503356 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4660. Min Act: -0.0000

Data Index: 840196 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1051029 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4835. Min Act: -0.0000

Data Index: 96930 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4696. Min Act: -0.0001

Data Index: 1234966 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4681. Min Act: -0.0001

Data Index: 226717 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4503. Min Act: -0.0000

Data Index: 539208 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1077753 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4552. Min Act: -0.0000

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4340. Min Act: -0.0001

Data Index: 311769 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.5012. Min Act: -0.0000

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1339206 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4646. Min Act: -0.0000

Data Index: 687694 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4684. Min Act: -0.0001

Data Index: 233872 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4673. Min Act: -0.0001

Data Index: 402436 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4785. Min Act: -0.0001

Data Index: 256702 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4532. Min Act: -0.0000

Data Index: 390746 (C4 (Web Text))

Max Activating Token Index: 296