Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 255 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.3867. Min Range: -7.3867

Max Act: 7.3867. Min Act: -0.0000

Data Index: 327942 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 7.3867. Min Range: -7.3867

Max Act: 7.2049. Min Act: -0.0000

Data Index: 753256 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.7643. Min Act: -0.0000

Data Index: 886435 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.7612. Min Act: -0.0000

Data Index: 10518 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.5628. Min Act: -0.0000

Data Index: 459452 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.3523. Min Act: -0.0000

Data Index: 584007 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.3811. Min Act: -0.0000

Data Index: 702161 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.3703. Min Act: -0.0000

Data Index: 130624 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 7.3867. Min Range: -7.3867

Max Act: 6.1419. Min Act: -0.0000

Data Index: 862589 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.8897. Min Act: -0.0000

Data Index: 1142462 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.9403. Min Act: -0.0000

Data Index: 133884 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.7570. Min Act: -0.0000

Data Index: 638206 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.9546. Min Act: -0.0000

Data Index: 1265765 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.7471. Min Act: -0.0000

Data Index: 1183364 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.5026. Min Act: -0.0000

Data Index: 178735 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.4704. Min Act: -0.0000

Data Index: 996637 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.4483. Min Act: -0.0000

Data Index: 30881 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.3769. Min Act: -0.0000

Data Index: 133706 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 7.3867. Min Range: -7.3867

Max Act: 5.1957. Min Act: -0.0000

Data Index: 1218271 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 7.3867. Min Range: -7.3867

Max Act: 4.9959. Min Act: -0.0000

Data Index: 709015 (C4 (Web Text))

Max Activating Token Index: 460