Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.8539. Min Act: -0.0000

Data Index: 468246 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.5115. Min Act: -0.0000

Data Index: 856644 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.1388. Min Act: -0.0000

Data Index: 569149 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.1194. Min Act: -0.0000

Data Index: 501150 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.1046. Min Act: -0.0000

Data Index: 37080 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.0878. Min Act: 0.0000

Data Index: 195626 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.8089. Min Act: -0.0000

Data Index: 889768 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1339554 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.9030. Min Act: 0.0000

Data Index: 282718 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.9693. Min Act: -0.0000

Data Index: 444289 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.6707. Min Act: 0.0000

Data Index: 406042 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.9552. Min Act: -0.0000

Data Index: 1311284 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.8461. Min Act: -0.0000

Data Index: 1318963 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.9280. Min Act: -0.0000

Data Index: 1106317 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 2.8539. Min Range: -2.8539

Max Act: 2.0356. Min Act: -0.0000

Data Index: 1357177 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.9033. Min Act: -0.0000

Data Index: 463768 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.7788. Min Act: -0.0000

Data Index: 612943 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.8646. Min Act: -0.0000

Data Index: 1189285 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.8679. Min Act: -0.0000

Data Index: 1065757 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 2.8539. Min Range: -2.8539

Max Act: 1.8337. Min Act: -0.0000

Data Index: 1210993 (C4 (Web Text))

Max Activating Token Index: 161