Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0711. Min Act: -0.0000

Data Index: 68228 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0397. Min Act: -0.0000

Data Index: 181789 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1082649 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9946. Min Act: -0.0000

Data Index: 596208 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1137884 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1094666 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1218499 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8491. Min Act: -0.0000

Data Index: 405794 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8336. Min Act: -0.0000

Data Index: 449649 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8977. Min Act: -0.0000

Data Index: 34548 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8055. Min Act: -0.0000

Data Index: 386720 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1137771 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1278637 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1054972 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7995. Min Act: -0.0000

Data Index: 739690 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1296258 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8035. Min Act: -0.0000

Data Index: 549533 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7763. Min Act: -0.0000

Data Index: 479380 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1352266 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7666. Min Act: -0.0000

Data Index: 356059 (C4 (Web Text))

Max Activating Token Index: 261