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

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

Neuron 4004 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3294. Min Range: -3.3294

Max Act: 3.3294. Min Act: -0.0000

Data Index: 603393 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.9823. Min Act: -0.0000

Data Index: 883831 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.8214. Min Act: -0.0000

Data Index: 962599 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.8066. Min Act: -0.0000

Data Index: 1006552 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.9606. Min Act: -0.0000

Data Index: 507970 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.5423. Min Act: -0.0000

Data Index: 709259 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.6578. Min Act: -0.0000

Data Index: 155838 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.7515. Min Act: -0.0000

Data Index: 742743 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.6580. Min Act: -0.0000

Data Index: 487072 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.8042. Min Act: -0.0000

Data Index: 600373 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.7618. Min Act: -0.0000

Data Index: 278022 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.6612. Min Act: -0.0000

Data Index: 1255933 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.7698. Min Act: -0.0000

Data Index: 630843 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.4817. Min Act: -0.0000

Data Index: 733025 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.2201. Min Act: -0.0000

Data Index: 181679 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.8130. Min Act: -0.0000

Data Index: 798015 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.4306. Min Act: -0.0000

Data Index: 760236 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.6769. Min Act: -0.0000

Data Index: 319693 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.6636. Min Act: -0.0000

Data Index: 631533 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 3.3294. Min Range: -3.3294

Max Act: 2.0612. Min Act: -0.0000

Data Index: 27720 (C4 (Web Text))

Max Activating Token Index: 821