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

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

Neuron 2478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0000

Data Index: 954181 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0599. Min Act: -0.0000

Data Index: 401222 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1348218 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0569. Min Act: -0.0000

Data Index: 525317 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0542. Min Act: -0.0000

Data Index: 548259 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0528. Min Act: -0.0000

Data Index: 350031 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1072311 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1056779 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0528. Min Act: -0.0000

Data Index: 803265 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0493. Min Act: -0.0000

Data Index: 672590 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0475. Min Act: -0.0000

Data Index: 709228 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1134984 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0489. Min Act: -0.0000

Data Index: 553564 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0496. Min Act: -0.0000

Data Index: 193093 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0456. Min Act: -0.0000

Data Index: 693984 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0474. Min Act: -0.0000

Data Index: 339544 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0451. Min Act: -0.0000

Data Index: 295307 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0464. Min Act: -0.0000

Data Index: 700316 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0480. Min Act: -0.0000

Data Index: 97727 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0447. Min Act: -0.0000

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 559