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

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

Neuron 4553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.7117. Min Act: -0.0000

Data Index: 1038034 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.7144. Min Act: -0.0000

Data Index: 574073 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6160. Min Act: -0.0000

Data Index: 810955 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6079. Min Act: -0.0000

Data Index: 1261598 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.6444. Min Act: -0.0000

Data Index: 450910 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.5903. Min Act: -0.0000

Data Index: 303005 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.5242. Min Act: -0.0000

Data Index: 864052 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.4395. Min Act: -0.0000

Data Index: 527298 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.4123. Min Act: -0.0000

Data Index: 36829 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3952. Min Act: -0.0000

Data Index: 403022 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3200. Min Act: -0.0000

Data Index: 799152 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3679. Min Act: -0.0000

Data Index: 291955 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1197610 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3234. Min Act: -0.0000

Data Index: 383372 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1250876 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3516. Min Act: -0.0000

Data Index: 331287 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3620. Min Act: -0.0000

Data Index: 306890 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1219995 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.7144. Min Range: -1.7144

Max Act: 1.2760. Min Act: -0.0000

Data Index: 1124668 (C4 (Web Text))

Max Activating Token Index: 636