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

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

Neuron 5914 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9702. Min Range: -4.9702

Max Act: 4.9702. Min Act: -0.0000

Data Index: 83565 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 4.9702. Min Range: -4.9702

Max Act: 4.9280. Min Act: -0.0000

Data Index: 1174241 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 4.9702. Min Range: -4.9702

Max Act: 4.3204. Min Act: -0.0000

Data Index: 794882 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 4.9702. Min Range: -4.9702

Max Act: 3.9651. Min Act: -0.0000

Data Index: 546464 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 4.9702. Min Range: -4.9702

Max Act: 3.9332. Min Act: -0.0000

Data Index: 1156625 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 4.9702. Min Range: -4.9702

Max Act: 3.7324. Min Act: -0.0000

Data Index: 660498 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 4.9702. Min Range: -4.9702

Max Act: 4.0090. Min Act: -0.0000

Data Index: 1026356 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 4.9702. Min Range: -4.9702

Max Act: 3.4533. Min Act: -0.0000

Data Index: 176874 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 4.9702. Min Range: -4.9702

Max Act: 3.1383. Min Act: -0.0000

Data Index: 1048676 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.8300. Min Act: -0.0000

Data Index: 764750 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.6281. Min Act: -0.0000

Data Index: 248929 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 4.9702. Min Range: -4.9702

Max Act: 1.8349. Min Act: -0.0000

Data Index: 576551 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 4.9702. Min Range: -4.9702

Max Act: 1.8788. Min Act: -0.0000

Data Index: 1235670 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.3410. Min Act: -0.0000

Data Index: 1104455 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.1059. Min Act: -0.0000

Data Index: 1335004 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.1923. Min Act: -0.0000

Data Index: 387577 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.1350. Min Act: -0.0000

Data Index: 1186093 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 4.9702. Min Range: -4.9702

Max Act: 1.9270. Min Act: -0.0000

Data Index: 178824 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 4.9702. Min Range: -4.9702

Max Act: 2.0302. Min Act: -0.0000

Data Index: 352667 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 4.9702. Min Range: -4.9702

Max Act: 1.7837. Min Act: -0.0000

Data Index: 280567 (C4 (Web Text))

Max Activating Token Index: 287