Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.1185. Min Act: -0.0001

Data Index: 273541 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0832. Min Act: -0.0001

Data Index: 984732 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0494. Min Act: -0.0001

Data Index: 374738 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9878. Min Act: -0.0001

Data Index: 928460 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0260. Min Act: -0.0001

Data Index: 492154 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0388. Min Act: -0.0001

Data Index: 1084012 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0404. Min Act: -0.0001

Data Index: 750192 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9365. Min Act: -0.0001

Data Index: 1101076 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0215. Min Act: -0.0001

Data Index: 269664 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9840. Min Act: -0.0001

Data Index: 339850 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9846. Min Act: -0.0001

Data Index: 195176 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1247715 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0397. Min Act: -0.0001

Data Index: 885901 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0137. Min Act: -0.0001

Data Index: 1333475 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9932. Min Act: -0.0001

Data Index: 1077622 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0004. Min Act: -0.0001

Data Index: 524609 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9658. Min Act: -0.0001

Data Index: 303665 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9920. Min Act: -0.0001

Data Index: 1234819 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.1185. Min Range: -1.1185

Max Act: 0.9600. Min Act: -0.0001

Data Index: 287309 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.1185. Min Range: -1.1185

Max Act: 1.0178. Min Act: -0.0001

Data Index: 908564 (C4 (Web Text))

Max Activating Token Index: 601