Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2221 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2365. Min Act: -0.0003

Data Index: 103215 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2361. Min Act: -0.0003

Data Index: 252222 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2325. Min Act: -0.0003

Data Index: 1195619 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2456. Min Act: -0.0003

Data Index: 952578 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2271. Min Act: -0.0003

Data Index: 1018698 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2324. Min Act: -0.0003

Data Index: 463225 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2267. Min Act: -0.0003

Data Index: 1210783 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2186. Min Act: -0.0003

Data Index: 1295713 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2525. Min Act: -0.0003

Data Index: 910864 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2093. Min Act: -0.0003

Data Index: 87117 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2248. Min Act: -0.0003

Data Index: 344030 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2144. Min Act: -0.0003

Data Index: 815916 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2206. Min Act: -0.0003

Data Index: 548888 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2207. Min Act: -0.0003

Data Index: 943592 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2121. Min Act: -0.0004

Data Index: 1226774 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2105. Min Act: -0.0003

Data Index: 240356 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2194. Min Act: -0.0003

Data Index: 1242313 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2267. Min Act: -0.0003

Data Index: 1177122 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2101. Min Act: -0.0003

Data Index: 727804 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2248. Min Act: -0.0003

Data Index: 1305642 (C4 (Web Text))

Max Activating Token Index: 578