Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1076 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0003

Data Index: 948041 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1137. Min Act: -0.0003

Data Index: 542531 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1107. Min Act: -0.0003

Data Index: 155954 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1011. Min Act: -0.0003

Data Index: 99502 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1015. Min Act: -0.0003

Data Index: 477694 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1035. Min Act: -0.0003

Data Index: 717103 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1038. Min Act: -0.0003

Data Index: 444822 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0992. Min Act: -0.0003

Data Index: 675765 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1003. Min Act: -0.0003

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0921. Min Act: -0.0003

Data Index: 386534 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0964. Min Act: -0.0003

Data Index: 560554 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0952. Min Act: -0.0003

Data Index: 665211 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0970. Min Act: -0.0003

Data Index: 148078 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0982. Min Act: -0.0003

Data Index: 66368 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0961. Min Act: -0.0003

Data Index: 539358 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0990. Min Act: -0.0003

Data Index: 398008 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0957. Min Act: -0.0003

Data Index: 1307563 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0966. Min Act: -0.0003

Data Index: 770497 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0929. Min Act: -0.0003

Data Index: 227207 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0935. Min Act: -0.0003

Data Index: 304651 (C4 (Web Text))

Max Activating Token Index: 487