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

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

Neuron 66 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2580. Min Act: -0.0000

Data Index: 559690 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1326875 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2479. Min Act: -0.0000

Data Index: 46740 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1287855 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2337. Min Act: -0.0000

Data Index: 808869 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2419. Min Act: -0.0000

Data Index: 116335 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2182. Min Act: -0.0000

Data Index: 290760 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1101918 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2117. Min Act: -0.0000

Data Index: 747216 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2035. Min Act: -0.0000

Data Index: 669977 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2146. Min Act: -0.0000

Data Index: 148826 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2040. Min Act: -0.0000

Data Index: 331943 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.1901. Min Act: -0.0000

Data Index: 184368 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2054. Min Act: -0.0000

Data Index: 717985 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.1972. Min Act: -0.0000

Data Index: 52212 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2137. Min Act: -0.0000

Data Index: 522086 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1013348 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.1958. Min Act: -0.0000

Data Index: 184816 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.1953. Min Act: -0.0000

Data Index: 748192 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.2583. Min Range: -0.2583

Max Act: 0.1937. Min Act: -0.0000

Data Index: 547982 (C4 (Web Text))

Max Activating Token Index: 223