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

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

Neuron 4817 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.6310. Min Act: -0.0000

Data Index: 493660 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.6538. Min Act: -0.0000

Data Index: 746108 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1280846 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5185. Min Act: -0.0000

Data Index: 958124 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1086597 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4766. Min Act: -0.0000

Data Index: 747693 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4924. Min Act: -0.0000

Data Index: 142572 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4541. Min Act: -0.0000

Data Index: 536012 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4844. Min Act: -0.0000

Data Index: 555139 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4591. Min Act: -0.0000

Data Index: 984346 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1067475 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4533. Min Act: -0.0000

Data Index: 673164 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1009630 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4206. Min Act: -0.0000

Data Index: 754564 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4463. Min Act: -0.0000

Data Index: 978847 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4437. Min Act: -0.0000

Data Index: 432469 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4402. Min Act: -0.0000

Data Index: 780261 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4328. Min Act: -0.0000

Data Index: 21221 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4318. Min Act: -0.0000

Data Index: 500397 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.6538. Min Range: -0.6538

Max Act: 0.4307. Min Act: -0.0000

Data Index: 612314 (C4 (Web Text))

Max Activating Token Index: 534