Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1951 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0005

Data Index: 397877 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0671. Min Act: -0.0005

Data Index: 836289 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0638. Min Act: -0.0005

Data Index: 782777 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0640. Min Act: -0.0005

Data Index: 1224521 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0622. Min Act: -0.0005

Data Index: 718537 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0639. Min Act: -0.0005

Data Index: 709144 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0629. Min Act: -0.0005

Data Index: 1004381 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0612. Min Act: -0.0005

Data Index: 1055727 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0613. Min Act: -0.0005

Data Index: 54972 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0607. Min Act: -0.0005

Data Index: 541592 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0587. Min Act: -0.0005

Data Index: 1080427 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0596. Min Act: -0.0005

Data Index: 110086 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0557. Min Act: -0.0005

Data Index: 943968 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0585. Min Act: -0.0005

Data Index: 1309448 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0590. Min Act: -0.0005

Data Index: 254317 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0574. Min Act: -0.0005

Data Index: 1002897 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0556. Min Act: -0.0005

Data Index: 1341209 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0573. Min Act: -0.0005

Data Index: 542517 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0549. Min Act: -0.0005

Data Index: 694263 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0534. Min Act: -0.0005

Data Index: 307972 (C4 (Web Text))

Max Activating Token Index: 644