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

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

Neuron 3467 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.9627. Min Act: -0.0000

Data Index: 1160423 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.8852. Min Act: -0.0000

Data Index: 1274754 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.5946. Min Act: -0.0000

Data Index: 332034 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.8425. Min Act: -0.0000

Data Index: 754478 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.5597. Min Act: -0.0000

Data Index: 1355439 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.4498. Min Act: -0.0000

Data Index: 392693 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.2828. Min Act: -0.0000

Data Index: 419390 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.3477. Min Act: -0.0000

Data Index: 625377 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.3562. Min Act: 0.0000

Data Index: 1129757 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.4596. Min Act: -0.0000

Data Index: 129398 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.2692. Min Act: -0.0000

Data Index: 247500 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.3757. Min Act: 0.0000

Data Index: 546970 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.2143. Min Act: -0.0000

Data Index: 69254 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.2317. Min Act: -0.0000

Data Index: 307775 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.1094. Min Act: -0.0000

Data Index: 945944 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.4482. Min Act: -0.0000

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.2227. Min Act: -0.0000

Data Index: 925082 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.2283. Min Act: -0.0000

Data Index: 1020733 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.1958. Min Act: -0.0000

Data Index: 634208 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.9627. Min Range: -2.9627

Max Act: 2.0370. Min Act: -0.0000

Data Index: 15040 (C4 (Web Text))

Max Activating Token Index: 835