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

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

Neuron 2004 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: 0.2134. Min Range: -0.2134

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1357505 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1764. Min Act: -0.0000

Data Index: 575914 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1268419 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1793. Min Act: -0.0000

Data Index: 146533 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1878. Min Act: -0.0000

Data Index: 160207 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1591. Min Act: -0.0000

Data Index: 442668 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1691. Min Act: -0.0000

Data Index: 731599 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1591. Min Act: -0.0000

Data Index: 784268 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1563. Min Act: -0.0000

Data Index: 958767 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1628. Min Act: -0.0000

Data Index: 669963 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1284434 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1058161 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1355. Min Act: -0.0000

Data Index: 865635 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1177897 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1345. Min Act: -0.0000

Data Index: 509521 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1371. Min Act: -0.0000

Data Index: 996488 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1361. Min Act: -0.0000

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1335505 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1519. Min Act: -0.0000

Data Index: 593002 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.2134. Min Range: -0.2134

Max Act: 0.1313. Min Act: -0.0000

Data Index: 944891 (C4 (Web Text))

Max Activating Token Index: 195