Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 251 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0003

Data Index: 774703 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1264741 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1010984 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0618. Min Act: -0.0003

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1038872 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0643. Min Act: -0.0003

Data Index: 870743 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0596. Min Act: -0.0003

Data Index: 883682 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0568. Min Act: -0.0003

Data Index: 167390 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0609. Min Act: -0.0003

Data Index: 174578 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0613. Min Act: -0.0003

Data Index: 514999 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1322992 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0592. Min Act: -0.0003

Data Index: 50036 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0588. Min Act: -0.0003

Data Index: 938019 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0604. Min Act: -0.0003

Data Index: 328654 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1338349 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0592. Min Act: -0.0003

Data Index: 429818 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1231829 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0588. Min Act: -0.0003

Data Index: 133062 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1062045 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0600. Min Act: -0.0003

Data Index: 176037 (C4 (Web Text))

Max Activating Token Index: 181