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

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

Neuron 1299 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.7816. Min Act: 0.0000

Data Index: 1614093 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.6646. Min Act: -0.0000

Data Index: 1594267 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.4414. Min Act: -0.0000

Data Index: 1503312 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.5841. Min Act: -0.0000

Data Index: 1579735 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1607177 (Python Code)

Max Activating Token Index: 698

Text #5

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1641537 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1384349 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1514161 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1641866 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1538540 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1644892 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1508117 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1607861 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1402692 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1412402 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.0902. Min Act: -0.0000

Data Index: 57669 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1544230 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1446219 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.0780. Min Act: 0.0000

Data Index: 1604583 (Python Code)

Max Activating Token Index: 228

Text #19

Max Range: 1.7816. Min Range: -1.7816

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1578723 (Python Code)

Max Activating Token Index: 729