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

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

Neuron 2415 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1297282 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2759. Min Act: -0.0000

Data Index: 454594 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1355770 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2878. Min Act: -0.0000

Data Index: 699794 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2763. Min Act: -0.0000

Data Index: 242306 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2865. Min Act: -0.0000

Data Index: 143606 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1142352 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2595. Min Act: -0.0000

Data Index: 324791 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1103412 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1308978 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2646. Min Act: -0.0000

Data Index: 684714 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2550. Min Act: -0.0000

Data Index: 439782 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2446. Min Act: -0.0000

Data Index: 311061 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1329221 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2465. Min Act: -0.0000

Data Index: 569197 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1293865 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2624. Min Act: -0.0000

Data Index: 119008 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2559. Min Act: -0.0000

Data Index: 27723 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2578. Min Act: -0.0000

Data Index: 944808 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2408. Min Act: -0.0000

Data Index: 374558 (C4 (Web Text))

Max Activating Token Index: 202