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

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

Neuron 2625 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: 1.7490. Min Range: -1.7490

Max Act: 1.7490. Min Act: -0.0000

Data Index: 1308869 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.4466. Min Act: -0.0000

Data Index: 716834 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.2995. Min Act: -0.0000

Data Index: 767356 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.4135. Min Act: -0.0000

Data Index: 194912 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.3019. Min Act: -0.0000

Data Index: 19825 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1626124 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.1787. Min Act: -0.0000

Data Index: 337088 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.0791. Min Act: -0.0000

Data Index: 1240691 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.1298. Min Act: -0.0000

Data Index: 523479 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.1213. Min Act: -0.0000

Data Index: 450960 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1122297 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 1.7490. Min Range: -1.7490

Max Act: 0.9655. Min Act: -0.0000

Data Index: 19986 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.0235. Min Act: -0.0000

Data Index: 987060 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1295109 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.0040. Min Act: -0.0000

Data Index: 363063 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.7490. Min Range: -1.7490

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1558246 (Python Code)

Max Activating Token Index: 764

Text #17

Max Range: 1.7490. Min Range: -1.7490

Max Act: 0.9525. Min Act: -0.0000

Data Index: 502 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.7490. Min Range: -1.7490

Max Act: 1.0179. Min Act: -0.0000

Data Index: 82198 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.7490. Min Range: -1.7490

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1289515 (C4 (Web Text))

Max Activating Token Index: 802