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

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

Neuron 4153 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2846. Min Act: -0.0000

Data Index: 659135 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1231875 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1240169 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2647. Min Act: -0.0000

Data Index: 876088 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2588. Min Act: -0.0000

Data Index: 233905 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1150429 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2335. Min Act: -0.0000

Data Index: 550398 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2486. Min Act: -0.0000

Data Index: 201283 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1189771 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1114171 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1234110 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2552. Min Act: -0.0000

Data Index: 225753 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1236391 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2630. Min Act: -0.0000

Data Index: 628516 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2521. Min Act: -0.0000

Data Index: 549867 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1315665 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2520. Min Act: -0.0000

Data Index: 746800 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1140828 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2513. Min Act: -0.0000

Data Index: 292644 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2472. Min Act: -0.0000

Data Index: 838172 (C4 (Web Text))

Max Activating Token Index: 250