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

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

Neuron 5579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1402. Min Range: -3.1402

Max Act: 3.1402. Min Act: -0.0000

Data Index: 18450 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.4498. Min Act: -0.0000

Data Index: 345538 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 3.1402. Min Range: -3.1402

Max Act: 2.1160. Min Act: -0.0000

Data Index: 705900 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.9814. Min Act: -0.0000

Data Index: 465715 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.9418. Min Act: -0.0000

Data Index: 197567 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.6115. Min Act: -0.0000

Data Index: 285755 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.4008. Min Act: -0.0000

Data Index: 1193105 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3947. Min Act: -0.0000

Data Index: 315419 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1323130 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.4413. Min Act: -0.0000

Data Index: 310179 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.5073. Min Act: -0.0000

Data Index: 416894 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3763. Min Act: 0.0000

Data Index: 313003 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.2748. Min Act: -0.0000

Data Index: 508374 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3936. Min Act: 0.0000

Data Index: 511495 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3814. Min Act: -0.0000

Data Index: 159266 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3648. Min Act: -0.0000

Data Index: 476129 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3631. Min Act: -0.0000

Data Index: 255791 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1310108 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1133771 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.1402. Min Range: -3.1402

Max Act: 1.2477. Min Act: -0.0000

Data Index: 416425 (C4 (Web Text))

Max Activating Token Index: 1011