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

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

Neuron 462 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0477. Min Act: -0.0006

Data Index: 314465 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0006

Data Index: 887346 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0424. Min Act: -0.0006

Data Index: 172466 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0449. Min Act: -0.0006

Data Index: 449193 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0454. Min Act: -0.0006

Data Index: 699419 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0426. Min Act: -0.0006

Data Index: 771977 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1325432 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0398. Min Act: -0.0006

Data Index: 68691 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0417. Min Act: -0.0006

Data Index: 569321 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0410. Min Act: -0.0006

Data Index: 722245 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0407. Min Act: -0.0006

Data Index: 977738 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0407. Min Act: -0.0006

Data Index: 925018 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0397. Min Act: -0.0006

Data Index: 793199 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1352941 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0404. Min Act: -0.0006

Data Index: 286176 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1215049 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0400. Min Act: -0.0006

Data Index: 781290 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1214009 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0400. Min Act: -0.0006

Data Index: 612130 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0392. Min Act: -0.0006

Data Index: 438100 (C4 (Web Text))

Max Activating Token Index: 313