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

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

Neuron 4470 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.7673. Min Act: -0.0002

Data Index: 1171278 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.7176. Min Act: -0.0003

Data Index: 17777 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6092. Min Act: -0.0002

Data Index: 278674 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6471. Min Act: -0.0003

Data Index: 142089 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6192. Min Act: -0.0003

Data Index: 693786 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5409. Min Act: -0.0002

Data Index: 772310 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5213. Min Act: -0.0002

Data Index: 622640 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5307. Min Act: -0.0003

Data Index: 277306 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5336. Min Act: -0.0002

Data Index: 485265 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5145. Min Act: -0.0003

Data Index: 1299672 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4975. Min Act: -0.0002

Data Index: 198492 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5052. Min Act: -0.0002

Data Index: 1009609 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5032. Min Act: -0.0002

Data Index: 816712 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5025. Min Act: -0.0002

Data Index: 1170832 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4612. Min Act: -0.0003

Data Index: 294256 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4482. Min Act: -0.0002

Data Index: 216775 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4847. Min Act: -0.0003

Data Index: 31061 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4322. Min Act: -0.0003

Data Index: 589484 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4040. Min Act: -0.0002

Data Index: 1357680 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.4350. Min Act: -0.0003

Data Index: 873265 (C4 (Web Text))

Max Activating Token Index: 379