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

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

Neuron 2041 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: 0.3175. Min Range: -0.3175

Max Act: 0.3175. Min Act: -0.0003

Data Index: 645912 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2717. Min Act: -0.0003

Data Index: 1235738 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2618. Min Act: -0.0002

Data Index: 1109498 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2614. Min Act: -0.0003

Data Index: 55630 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2607. Min Act: -0.0003

Data Index: 1011725 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2609. Min Act: -0.0003

Data Index: 517115 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2605. Min Act: -0.0003

Data Index: 573067 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2611. Min Act: -0.0003

Data Index: 1046253 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2563. Min Act: -0.0003

Data Index: 366833 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2609. Min Act: -0.0002

Data Index: 747761 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2561. Min Act: -0.0003

Data Index: 1017291 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2601. Min Act: -0.0002

Data Index: 1060411 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2578. Min Act: -0.0003

Data Index: 884484 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2597. Min Act: -0.0002

Data Index: 538429 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2577. Min Act: -0.0003

Data Index: 1203348 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2549. Min Act: -0.0003

Data Index: 541681 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2554. Min Act: -0.0003

Data Index: 339934 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2570. Min Act: -0.0003

Data Index: 797602 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2548. Min Act: -0.0003

Data Index: 108939 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.3175. Min Range: -0.3175

Max Act: 0.2572. Min Act: -0.0003

Data Index: 832893 (C4 (Web Text))

Max Activating Token Index: 374