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

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

Neuron 3867 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8642. Min Act: -0.0000

Data Index: 261515 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8633. Min Act: -0.0000

Data Index: 929146 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8529. Min Act: -0.0000

Data Index: 93795 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8068. Min Act: -0.0000

Data Index: 283787 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8526. Min Act: -0.0000

Data Index: 154244 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1249807 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6597. Min Act: -0.0000

Data Index: 984708 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6365. Min Act: -0.0000

Data Index: 260509 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5878. Min Act: -0.0000

Data Index: 667063 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1050233 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1320153 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5556. Min Act: -0.0000

Data Index: 512019 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1152651 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5382. Min Act: -0.0000

Data Index: 739775 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5193. Min Act: -0.0000

Data Index: 964542 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.5099. Min Act: -0.0000

Data Index: 707471 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.4577. Min Act: -0.0000

Data Index: 925058 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1235939 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.4732. Min Act: -0.0000

Data Index: 501106 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1190800 (C4 (Web Text))

Max Activating Token Index: 427