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

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

Neuron 256 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: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0005

Data Index: 637044 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0557. Min Act: -0.0005

Data Index: 587988 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0519. Min Act: -0.0005

Data Index: 484593 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0528. Min Act: -0.0005

Data Index: 296066 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0526. Min Act: -0.0005

Data Index: 912492 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0498. Min Act: -0.0005

Data Index: 364704 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0474. Min Act: -0.0005

Data Index: 319745 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0476. Min Act: -0.0005

Data Index: 483709 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0465. Min Act: -0.0005

Data Index: 797675 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0462. Min Act: -0.0005

Data Index: 991475 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0479. Min Act: -0.0005

Data Index: 249276 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0506. Min Act: -0.0005

Data Index: 946060 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0471. Min Act: -0.0005

Data Index: 267108 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0458. Min Act: -0.0005

Data Index: 497401 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0474. Min Act: -0.0005

Data Index: 157873 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0473. Min Act: -0.0005

Data Index: 929940 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0477. Min Act: -0.0005

Data Index: 109466 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1197442 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0431. Min Act: -0.0005

Data Index: 465319 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0439. Min Act: -0.0005

Data Index: 347264 (C4 (Web Text))

Max Activating Token Index: 184