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

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

Neuron 1140 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: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0006

Data Index: 766324 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0623. Min Act: -0.0006

Data Index: 1277516 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0570. Min Act: -0.0006

Data Index: 439164 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0532. Min Act: -0.0006

Data Index: 1356321 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0507. Min Act: -0.0006

Data Index: 143741 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0449. Min Act: -0.0006

Data Index: 88540 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0496. Min Act: -0.0006

Data Index: 1145390 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1058242 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0407. Min Act: -0.0006

Data Index: 426480 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0429. Min Act: -0.0006

Data Index: 941949 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1278609 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1026720 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0384. Min Act: -0.0006

Data Index: 184986 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0467. Min Act: -0.0006

Data Index: 1264934 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0415. Min Act: -0.0006

Data Index: 686310 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0413. Min Act: -0.0006

Data Index: 239222 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0447. Min Act: -0.0006

Data Index: 1116256 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0437. Min Act: -0.0006

Data Index: 291414 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1134313 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0407. Min Act: -0.0006

Data Index: 1008535 (C4 (Web Text))

Max Activating Token Index: 918