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

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

Neuron 2003 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.3506. Min Act: -0.0000

Data Index: 1646552 (Python Code)

Max Activating Token Index: 613

Text #1

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.0301. Min Act: -0.0000

Data Index: 434641 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.9549. Min Act: -0.0000

Data Index: 1494852 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.0510. Min Act: -0.0000

Data Index: 739838 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.1007. Min Act: -0.0000

Data Index: 132793 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.9980. Min Act: -0.0000

Data Index: 350901 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.0015. Min Act: -0.0000

Data Index: 905371 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.1319. Min Act: -0.0000

Data Index: 301818 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.3506. Min Range: -2.3506

Max Act: 2.0874. Min Act: -0.0000

Data Index: 366575 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7219. Min Act: -0.0000

Data Index: 1164077 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.9151. Min Act: -0.0000

Data Index: 1368915 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1060472 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7514. Min Act: -0.0000

Data Index: 1435717 (Python Code)

Max Activating Token Index: 860

Text #13

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.9288. Min Act: -0.0000

Data Index: 1606347 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7067. Min Act: -0.0000

Data Index: 1611518 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1457002 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7666. Min Act: -0.0000

Data Index: 1371150 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7593. Min Act: -0.0000

Data Index: 1494701 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7360. Min Act: -0.0000

Data Index: 36634 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 2.3506. Min Range: -2.3506

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1370662 (Python Code)

Max Activating Token Index: 155