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

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

Neuron 4317 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: 0.1083. Min Range: -0.1083

Max Act: 0.1083. Min Act: -0.0000

Data Index: 372682 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1015271 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0510. Min Act: -0.0001

Data Index: 675895 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1537985 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1560478 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0372. Min Act: -0.0001

Data Index: 992944 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0400. Min Act: -0.0001

Data Index: 320057 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1400860 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1310212 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1051960 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0383. Min Act: -0.0001

Data Index: 751645 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0361. Min Act: -0.0001

Data Index: 449153 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0404. Min Act: -0.0001

Data Index: 227680 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0370. Min Act: -0.0001

Data Index: 968607 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0366. Min Act: -0.0001

Data Index: 463282 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0318. Min Act: -0.0001

Data Index: 706382 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1588273 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0343. Min Act: -0.0001

Data Index: 583317 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1323622 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0337. Min Act: -0.0001

Data Index: 178398 (C4 (Web Text))

Max Activating Token Index: 73