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

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

Neuron 4350 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.5139. Min Act: -0.0002

Data Index: 373333 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4719. Min Act: -0.0002

Data Index: 192593 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4341. Min Act: -0.0002

Data Index: 233510 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4116. Min Act: -0.0002

Data Index: 475089 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4008. Min Act: -0.0002

Data Index: 76549 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.4060. Min Act: -0.0002

Data Index: 1097933 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3924. Min Act: -0.0002

Data Index: 917236 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3878. Min Act: -0.0002

Data Index: 220329 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3880. Min Act: -0.0002

Data Index: 759485 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3876. Min Act: -0.0002

Data Index: 38120 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3899. Min Act: -0.0002

Data Index: 1300481 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3870. Min Act: -0.0002

Data Index: 50437 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3821. Min Act: -0.0002

Data Index: 761852 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3813. Min Act: -0.0002

Data Index: 433489 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3852. Min Act: -0.0002

Data Index: 817496 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3773. Min Act: -0.0002

Data Index: 1357674 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3874. Min Act: -0.0002

Data Index: 532598 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3795. Min Act: -0.0002

Data Index: 29789 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3756. Min Act: -0.0002

Data Index: 365262 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.5139. Min Range: -0.5139

Max Act: 0.3688. Min Act: -0.0002

Data Index: 26901 (C4 (Web Text))

Max Activating Token Index: 27