Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0005

Data Index: 1321834 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0462. Min Act: -0.0005

Data Index: 411330 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0471. Min Act: -0.0005

Data Index: 914616 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0461. Min Act: -0.0005

Data Index: 882537 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0458. Min Act: -0.0005

Data Index: 176827 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0453. Min Act: -0.0005

Data Index: 123481 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0453. Min Act: -0.0005

Data Index: 109014 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0461. Min Act: -0.0005

Data Index: 1175502 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0455. Min Act: -0.0005

Data Index: 301676 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0434. Min Act: -0.0005

Data Index: 182097 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0434. Min Act: -0.0005

Data Index: 123138 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1000557 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0441. Min Act: -0.0005

Data Index: 680096 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0448. Min Act: -0.0005

Data Index: 560091 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0410. Min Act: -0.0005

Data Index: 856818 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0430. Min Act: -0.0005

Data Index: 565587 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1009704 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0439. Min Act: -0.0005

Data Index: 890758 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0427. Min Act: -0.0005

Data Index: 654793 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0411. Min Act: -0.0005

Data Index: 531040 (C4 (Web Text))

Max Activating Token Index: 487