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

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

Neuron 4659 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3146. Min Range: -3.3146

Max Act: 3.3146. Min Act: -0.0000

Data Index: 530816 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.8830. Min Act: -0.0000

Data Index: 52704 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.3146. Min Range: -3.3146

Max Act: 3.0337. Min Act: -0.0000

Data Index: 1205027 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.7485. Min Act: -0.0000

Data Index: 1258841 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.7154. Min Act: -0.0000

Data Index: 634767 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.4369. Min Act: -0.0000

Data Index: 785787 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.3449. Min Act: -0.0000

Data Index: 820402 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.4322. Min Act: -0.0000

Data Index: 256550 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.3295. Min Act: -0.0000

Data Index: 1294451 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.2805. Min Act: -0.0000

Data Index: 282324 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.1618. Min Act: -0.0000

Data Index: 90513 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.1518. Min Act: -0.0000

Data Index: 488127 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.0495. Min Act: -0.0000

Data Index: 775309 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.1622. Min Act: -0.0000

Data Index: 879509 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 3.3146. Min Range: -3.3146

Max Act: 1.8621. Min Act: -0.0000

Data Index: 698562 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 3.3146. Min Range: -3.3146

Max Act: 2.1131. Min Act: -0.0000

Data Index: 1275042 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 3.3146. Min Range: -3.3146

Max Act: 1.8347. Min Act: -0.0000

Data Index: 1382339 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 3.3146. Min Range: -3.3146

Max Act: 1.9391. Min Act: -0.0000

Data Index: 675880 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 3.3146. Min Range: -3.3146

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1067621 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.3146. Min Range: -3.3146

Max Act: 1.8724. Min Act: -0.0000

Data Index: 437533 (C4 (Web Text))

Max Activating Token Index: 429