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

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

Neuron 4450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.1463. Min Act: -0.0000

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0624. Min Act: -0.0000

Data Index: 313999 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0627. Min Act: -0.0000

Data Index: 193388 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1065460 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1020858 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9482. Min Act: -0.0000

Data Index: 31498 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1331597 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9209. Min Act: -0.0000

Data Index: 251773 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0197. Min Act: -0.0000

Data Index: 287059 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8723. Min Act: -0.0000

Data Index: 561855 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8766. Min Act: -0.0000

Data Index: 861986 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9015. Min Act: -0.0000

Data Index: 25024 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1212839 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9250. Min Act: -0.0000

Data Index: 885717 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1297963 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8951. Min Act: -0.0000

Data Index: 583200 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9136. Min Act: -0.0000

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9389. Min Act: -0.0000

Data Index: 97096 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8844. Min Act: -0.0000

Data Index: 113040 (C4 (Web Text))

Max Activating Token Index: 655