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

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

Neuron 4860 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4823. Min Act: -0.0000

Data Index: 586408 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4758. Min Act: -0.0000

Data Index: 513877 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4453. Min Act: -0.0000

Data Index: 569430 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4167. Min Act: -0.0000

Data Index: 961708 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1018638 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3481. Min Act: -0.0000

Data Index: 817520 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3555. Min Act: -0.0000

Data Index: 378678 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1051563 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3500. Min Act: -0.0000

Data Index: 575622 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3131. Min Act: -0.0000

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2818. Min Act: -0.0000

Data Index: 429978 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2699. Min Act: -0.0000

Data Index: 348687 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1042622 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2652. Min Act: -0.0000

Data Index: 779724 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1107175 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2688. Min Act: -0.0000

Data Index: 653805 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1284419 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2591. Min Act: -0.0000

Data Index: 981748 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2664. Min Act: -0.0000

Data Index: 656825 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.2408. Min Act: -0.0000

Data Index: 517732 (C4 (Web Text))

Max Activating Token Index: 230