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

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

Neuron 2430 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7306. Min Range: -1.7306

Max Act: 1.7306. Min Act: 0.0000

Data Index: 1003327 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 1.7306. Min Range: -1.7306

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1004544 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.7306. Min Range: -1.7306

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1209079 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.7306. Min Range: -1.7306

Max Act: 1.0388. Min Act: -0.0000

Data Index: 565274 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.7306. Min Range: -1.7306

Max Act: 1.0034. Min Act: -0.0000

Data Index: 983396 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.8327. Min Act: -0.0000

Data Index: 671116 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.8152. Min Act: 0.0000

Data Index: 1071514 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.8132. Min Act: -0.0000

Data Index: 349764 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.8629. Min Act: -0.0000

Data Index: 914161 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.7795. Min Act: 0.0000

Data Index: 469438 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.8076. Min Act: -0.0000

Data Index: 668283 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.7120. Min Act: 0.0000

Data Index: 68349 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6970. Min Act: -0.0000

Data Index: 62029 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6984. Min Act: -0.0000

Data Index: 315264 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6487. Min Act: -0.0000

Data Index: 427382 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6823. Min Act: 0.0000

Data Index: 389660 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.7135. Min Act: 0.0000

Data Index: 300743 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6661. Min Act: 0.0001

Data Index: 942256 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6356. Min Act: -0.0000

Data Index: 164080 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 1.7306. Min Range: -1.7306

Max Act: 0.6322. Min Act: -0.0000

Data Index: 38840 (C4 (Web Text))

Max Activating Token Index: 1014