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

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

Neuron 4853 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: 2.7708. Min Range: -2.7708

Max Act: 2.7708. Min Act: -0.0000

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.2142. Min Act: -0.0000

Data Index: 969966 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.4081. Min Act: -0.0000

Data Index: 1101428 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.3921. Min Act: -0.0000

Data Index: 186216 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.4277. Min Act: -0.0000

Data Index: 719913 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.2718. Min Act: -0.0000

Data Index: 1268135 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.2378. Min Act: -0.0000

Data Index: 914579 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.2975. Min Act: -0.0000

Data Index: 531356 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.2188. Min Act: -0.0000

Data Index: 634288 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.2537. Min Act: -0.0000

Data Index: 979497 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.1368. Min Act: -0.0000

Data Index: 643227 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.9850. Min Act: -0.0000

Data Index: 1271448 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.1623. Min Act: -0.0000

Data Index: 649423 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.1637. Min Act: -0.0000

Data Index: 13800 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1037135 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.1130. Min Act: -0.0000

Data Index: 1050380 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.0649. Min Act: -0.0000

Data Index: 1299979 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.9333. Min Act: -0.0000

Data Index: 1344510 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.1451. Min Act: -0.0000

Data Index: 1150177 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.0277. Min Act: -0.0000

Data Index: 772246 (C4 (Web Text))

Max Activating Token Index: 296