Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 967 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4839. Min Act: -0.0000

Data Index: 637108 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1074527 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4072. Min Act: -0.0000

Data Index: 684852 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4207. Min Act: -0.0000

Data Index: 728683 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4066. Min Act: -0.0000

Data Index: 423205 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4041. Min Act: -0.0000

Data Index: 192905 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1041989 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3867. Min Act: -0.0000

Data Index: 219446 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3786. Min Act: -0.0000

Data Index: 993095 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3740. Min Act: -0.0000

Data Index: 725146 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1198894 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1278128 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3662. Min Act: -0.0000

Data Index: 475200 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1299633 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1457090 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3613. Min Act: -0.0000

Data Index: 853570 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3678. Min Act: 0.0000

Data Index: 399909 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3511. Min Act: -0.0000

Data Index: 170424 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1364809 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1212899 (C4 (Web Text))

Max Activating Token Index: 172