Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1291. Min Act: -0.0000

Data Index: 439916 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1195. Min Act: -0.0000

Data Index: 314260 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1145. Min Act: -0.0000

Data Index: 803547 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1128. Min Act: -0.0000

Data Index: 950736 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1004. Min Act: -0.0000

Data Index: 83896 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1005. Min Act: -0.0000

Data Index: 532651 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0934. Min Act: -0.0000

Data Index: 735810 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1213275 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0928. Min Act: -0.0000

Data Index: 437382 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0991. Min Act: -0.0001

Data Index: 216780 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.1020. Min Act: -0.0000

Data Index: 11576 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0960. Min Act: -0.0000

Data Index: 943068 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0945. Min Act: -0.0000

Data Index: 457327 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0907. Min Act: -0.0000

Data Index: 853510 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0868. Min Act: -0.0000

Data Index: 492609 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0899. Min Act: -0.0001

Data Index: 611635 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0917. Min Act: -0.0000

Data Index: 212375 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0881. Min Act: -0.0000

Data Index: 197425 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1176082 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.1291. Min Range: -0.1291

Max Act: 0.0865. Min Act: -0.0000

Data Index: 626287 (C4 (Web Text))

Max Activating Token Index: 409