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

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

Neuron 3530 in Layer 9

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: 1.4596. Min Act: -0.0000

Data Index: 910995 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.4832. Min Act: -0.0000

Data Index: 1601325 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1446019 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.3177. Min Act: -0.0000

Data Index: 1626497 (Python Code)

Max Activating Token Index: 881

Text #4

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1614363 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1546392 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.3050. Min Act: -0.0000

Data Index: 1655646 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1646037 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1306275 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1264257 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1600356 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1231784 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1908. Min Act: -0.0000

Data Index: 847583 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1518887 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1016924 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1500971 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1142306 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0779. Min Act: -0.0000

Data Index: 964317 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1421835 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 1.4832. Min Range: -1.4832

Max Act: 1.0428. Min Act: -0.0000

Data Index: 687028 (C4 (Web Text))

Max Activating Token Index: 801