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

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

Neuron 1133 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1633. Min Range: -2.1633

Max Act: 2.1554. Min Act: -0.0000

Data Index: 599479 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.1633. Min Range: -2.1633

Max Act: 2.1086. Min Act: -0.0000

Data Index: 1158292 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9967. Min Act: -0.0000

Data Index: 15914 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9594. Min Act: -0.0000

Data Index: 928498 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 2.1633. Min Range: -2.1633

Max Act: 2.1633. Min Act: -0.0000

Data Index: 912311 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 2.1633. Min Range: -2.1633

Max Act: 2.0050. Min Act: -0.0000

Data Index: 110464 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9489. Min Act: -0.0000

Data Index: 694409 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9266. Min Act: -0.0000

Data Index: 702417 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9401. Min Act: -0.0000

Data Index: 1023847 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.1633. Min Range: -2.1633

Max Act: 2.0332. Min Act: -0.0000

Data Index: 995745 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9093. Min Act: -0.0000

Data Index: 400396 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.9683. Min Act: -0.0000

Data Index: 666993 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1318258 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8544. Min Act: -0.0000

Data Index: 672149 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8290. Min Act: -0.0000

Data Index: 707366 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.7286. Min Act: -0.0000

Data Index: 1086529 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6654. Min Act: -0.0000

Data Index: 429716 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.8332. Min Act: -0.0000

Data Index: 1214810 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.7289. Min Act: -0.0000

Data Index: 642125 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 2.1633. Min Range: -2.1633

Max Act: 1.6159. Min Act: -0.0000

Data Index: 868373 (C4 (Web Text))

Max Activating Token Index: 787