Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4340 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.7197. Min Act: -0.0002

Data Index: 35928 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.6240. Min Act: -0.0002

Data Index: 205193 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.3073. Min Act: -0.0002

Data Index: 20236 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.2423. Min Act: -0.0002

Data Index: 451306 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1936. Min Act: -0.0002

Data Index: 1084105 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1812. Min Act: -0.0003

Data Index: 594086 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1503. Min Act: -0.0002

Data Index: 571065 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1581. Min Act: -0.0002

Data Index: 481785 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0745. Min Act: -0.0002

Data Index: 1011233 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1764. Min Act: -0.0002

Data Index: 886791 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.1461. Min Act: -0.0002

Data Index: 185537 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0813. Min Act: -0.0002

Data Index: 679129 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0917. Min Act: -0.0002

Data Index: 1003025 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0196. Min Act: -0.0002

Data Index: 1227239 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0655. Min Act: -0.0002

Data Index: 1120357 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0144. Min Act: -0.0002

Data Index: 1157350 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0227. Min Act: -0.0002

Data Index: 957461 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.9682. Min Act: -0.0002

Data Index: 292175 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 2.7197. Min Range: -2.7197

Max Act: 2.0020. Min Act: -0.0002

Data Index: 391602 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.7197. Min Range: -2.7197

Max Act: 1.9934. Min Act: -0.0002

Data Index: 773646 (C4 (Web Text))

Max Activating Token Index: 598