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

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

Neuron 1061 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: 0.2875. Min Range: -0.2875

Max Act: 0.2875. Min Act: -0.0000

Data Index: 207976 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2658. Min Act: -0.0001

Data Index: 528452 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2420. Min Act: -0.0000

Data Index: 800923 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2224. Min Act: -0.0000

Data Index: 142879 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2303. Min Act: -0.0000

Data Index: 567217 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2230. Min Act: -0.0000

Data Index: 272763 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2178. Min Act: -0.0000

Data Index: 44 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1184186 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2117. Min Act: -0.0001

Data Index: 180763 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1082213 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2160. Min Act: -0.0000

Data Index: 394327 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2187. Min Act: -0.0001

Data Index: 235873 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1295006 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2100. Min Act: -0.0000

Data Index: 874463 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.1867. Min Act: -0.0001

Data Index: 444638 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2157. Min Act: -0.0000

Data Index: 59423 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1311699 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2223. Min Act: -0.0000

Data Index: 848045 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2057. Min Act: -0.0000

Data Index: 182658 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1063947 (C4 (Web Text))

Max Activating Token Index: 526