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

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

Neuron 5684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3937. Min Range: -4.3937

Max Act: 4.3937. Min Act: -0.0000

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 4.3937. Min Range: -4.3937

Max Act: 4.2060. Min Act: -0.0000

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 4.3937. Min Range: -4.3937

Max Act: 3.9329. Min Act: -0.0000

Data Index: 204555 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 4.3937. Min Range: -4.3937

Max Act: 3.7138. Min Act: -0.0000

Data Index: 833159 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 4.3937. Min Range: -4.3937

Max Act: 3.6284. Min Act: -0.0000

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 4.3937. Min Range: -4.3937

Max Act: 3.6152. Min Act: -0.0000

Data Index: 919869 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 4.3937. Min Range: -4.3937

Max Act: 3.1998. Min Act: -0.0000

Data Index: 491103 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.7415. Min Act: -0.0000

Data Index: 1190744 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.9641. Min Act: -0.0000

Data Index: 210223 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.6210. Min Act: -0.0000

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.4398. Min Act: -0.0000

Data Index: 447736 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.8173. Min Act: -0.0000

Data Index: 113089 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.1711. Min Act: -0.0000

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.0536. Min Act: -0.0000

Data Index: 202638 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.0321. Min Act: -0.0000

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 4.3937. Min Range: -4.3937

Max Act: 1.9899. Min Act: -0.0000

Data Index: 148627 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 4.3937. Min Range: -4.3937

Max Act: 1.8703. Min Act: -0.0000

Data Index: 141654 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 4.3937. Min Range: -4.3937

Max Act: 1.8371. Min Act: -0.0000

Data Index: 429242 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.0092. Min Act: -0.0000

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 4.3937. Min Range: -4.3937

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1237744 (C4 (Web Text))

Max Activating Token Index: 796