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

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

Neuron 3924 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6513. Min Range: -8.6513

Max Act: 8.6513. Min Act: -0.0001

Data Index: 528747 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 8.6513. Min Range: -8.6513

Max Act: 8.0542. Min Act: -0.0001

Data Index: 1082160 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 8.6513. Min Range: -8.6513

Max Act: 7.1575. Min Act: -0.0001

Data Index: 138001 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 8.6513. Min Range: -8.6513

Max Act: 6.3010. Min Act: -0.0001

Data Index: 418210 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 8.6513. Min Range: -8.6513

Max Act: 7.0826. Min Act: -0.0001

Data Index: 457901 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 8.6513. Min Range: -8.6513

Max Act: 6.5473. Min Act: -0.0001

Data Index: 277516 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 8.6513. Min Range: -8.6513

Max Act: 6.5685. Min Act: -0.0001

Data Index: 174065 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 8.6513. Min Range: -8.6513

Max Act: 6.4634. Min Act: -0.0001

Data Index: 1163329 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 8.6513. Min Range: -8.6513

Max Act: 6.4821. Min Act: -0.0001

Data Index: 506031 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.8957. Min Act: -0.0001

Data Index: 1126943 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.8985. Min Act: -0.0001

Data Index: 292714 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.7336. Min Act: -0.0001

Data Index: 546536 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.6953. Min Act: -0.0001

Data Index: 374443 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.7182. Min Act: -0.0001

Data Index: 356244 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.8042. Min Act: -0.0001

Data Index: 508806 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.7547. Min Act: -0.0001

Data Index: 1163920 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.7584. Min Act: -0.0001

Data Index: 862736 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.5426. Min Act: -0.0001

Data Index: 914087 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 8.6513. Min Range: -8.6513

Max Act: 5.1244. Min Act: -0.0001

Data Index: 723962 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 8.6513. Min Range: -8.6513

Max Act: 6.0177. Min Act: -0.0001

Data Index: 1048108 (C4 (Web Text))

Max Activating Token Index: 769