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

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

Neuron 3050 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: 2.2806. Min Range: -2.2806

Max Act: 2.2806. Min Act: -0.0002

Data Index: 677396 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 2.2806. Min Range: -2.2806

Max Act: 2.0876. Min Act: -0.0002

Data Index: 729191 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 2.2806. Min Range: -2.2806

Max Act: 2.0900. Min Act: -0.0002

Data Index: 488093 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 2.2806. Min Range: -2.2806

Max Act: 2.0900. Min Act: -0.0002

Data Index: 724172 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 2.2806. Min Range: -2.2806

Max Act: 2.1013. Min Act: -0.0002

Data Index: 1235336 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9983. Min Act: -0.0002

Data Index: 556071 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9729. Min Act: -0.0002

Data Index: 1127663 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9367. Min Act: -0.0002

Data Index: 356965 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9353. Min Act: -0.0002

Data Index: 537509 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 2.2806. Min Range: -2.2806

Max Act: 2.0143. Min Act: -0.0002

Data Index: 964418 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9740. Min Act: -0.0002

Data Index: 122174 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9587. Min Act: -0.0002

Data Index: 24753 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.8818. Min Act: -0.0002

Data Index: 1235369 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9269. Min Act: -0.0002

Data Index: 88218 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.8928. Min Act: -0.0002

Data Index: 111422 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9663. Min Act: -0.0002

Data Index: 1270218 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9114. Min Act: -0.0003

Data Index: 1145363 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.9299. Min Act: -0.0002

Data Index: 862986 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.8461. Min Act: -0.0002

Data Index: 297421 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 2.2806. Min Range: -2.2806

Max Act: 1.8810. Min Act: -0.0002

Data Index: 1299079 (C4 (Web Text))

Max Activating Token Index: 5