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

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

Neuron 1623 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9911. Min Range: -3.9911

Max Act: 3.7334. Min Act: -0.0000

Data Index: 570876 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 3.9911. Min Range: -3.9911

Max Act: 3.9911. Min Act: -0.0000

Data Index: 1546679 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 3.9911. Min Range: -3.9911

Max Act: 3.3543. Min Act: -0.0000

Data Index: 944916 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.9911. Min Range: -3.9911

Max Act: 3.4547. Min Act: -0.0000

Data Index: 781796 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.9430. Min Act: -0.0000

Data Index: 556405 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 3.9911. Min Range: -3.9911

Max Act: 3.0669. Min Act: -0.0000

Data Index: 1418835 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.8943. Min Act: -0.0000

Data Index: 980217 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.7955. Min Act: -0.0000

Data Index: 1169695 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 3.9911. Min Range: -3.9911

Max Act: 3.0229. Min Act: -0.0000

Data Index: 1232465 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.8710. Min Act: -0.0000

Data Index: 1145087 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.7971. Min Act: -0.0000

Data Index: 141226 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.9119. Min Act: -0.0000

Data Index: 804808 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.8597. Min Act: -0.0000

Data Index: 500174 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.8322. Min Act: -0.0000

Data Index: 317405 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.5653. Min Act: -0.0000

Data Index: 872602 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.7046. Min Act: -0.0000

Data Index: 823410 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.5288. Min Act: -0.0000

Data Index: 1510459 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.5307. Min Act: -0.0000

Data Index: 436360 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.5057. Min Act: 0.0000

Data Index: 676921 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 3.9911. Min Range: -3.9911

Max Act: 2.6414. Min Act: -0.0000

Data Index: 1115391 (C4 (Web Text))

Max Activating Token Index: 984