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

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

Neuron 3153 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1098. Min Range: -3.1098

Max Act: 2.9540. Min Act: -0.0000

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 3.1098. Min Range: -3.1098

Max Act: 3.1098. Min Act: -0.0000

Data Index: 1133375 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 3.1098. Min Range: -3.1098

Max Act: 2.5985. Min Act: -0.0000

Data Index: 496707 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 3.1098. Min Range: -3.1098

Max Act: 2.5394. Min Act: -0.0000

Data Index: 318788 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 3.1098. Min Range: -3.1098

Max Act: 2.2691. Min Act: -0.0000

Data Index: 947560 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1097237 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.8682. Min Act: -0.0000

Data Index: 113089 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 3.1098. Min Range: -3.1098

Max Act: 2.1612. Min Act: -0.0000

Data Index: 344573 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 3.1098. Min Range: -3.1098

Max Act: 2.0225. Min Act: -0.0000

Data Index: 1463597 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.8819. Min Act: -0.0000

Data Index: 866550 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.8728. Min Act: -0.0000

Data Index: 941632 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.8732. Min Act: -0.0000

Data Index: 1375038 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.9756. Min Act: -0.0000

Data Index: 1225079 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.8168. Min Act: -0.0000

Data Index: 333446 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.6643. Min Act: -0.0000

Data Index: 203157 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.7454. Min Act: -0.0000

Data Index: 955346 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.7074. Min Act: -0.0000

Data Index: 313843 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.7291. Min Act: -0.0000

Data Index: 521781 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.6109. Min Act: -0.0000

Data Index: 609160 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 3.1098. Min Range: -3.1098

Max Act: 1.6906. Min Act: -0.0000

Data Index: 411569 (C4 (Web Text))

Max Activating Token Index: 565