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

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

Neuron 5440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.4832. Min Act: -0.0000

Data Index: 1594834 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0834. Min Act: -0.0000

Data Index: 426071 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1552219 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1367712 (Python Code)

Max Activating Token Index: 528

Text #4

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2031. Min Act: -0.0000

Data Index: 768565 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1542474 (Python Code)

Max Activating Token Index: 209

Text #6

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1491154 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1565613 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1380307 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0962. Min Act: -0.0000

Data Index: 134607 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1055. Min Act: -0.0000

Data Index: 562042 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1453385 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2334. Min Act: -0.0000

Data Index: 1524517 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1609615 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1098617 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1457232 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 1.4832. Min Range: -1.4832

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1583529 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0525. Min Act: -0.0000

Data Index: 721214 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0101. Min Act: -0.0000

Data Index: 151923 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.4832. Min Range: -1.4832

Max Act: 0.9407. Min Act: -0.0000

Data Index: 483681 (C4 (Web Text))

Max Activating Token Index: 333