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

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

Neuron 4377 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: 0.6689. Min Range: -0.6689

Max Act: 0.6517. Min Act: -0.0002

Data Index: 464728 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6689. Min Act: -0.0002

Data Index: 383395 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6595. Min Act: -0.0002

Data Index: 1207388 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6479. Min Act: -0.0002

Data Index: 317084 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6479. Min Act: -0.0003

Data Index: 309594 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6451. Min Act: -0.0002

Data Index: 484064 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6337. Min Act: -0.0002

Data Index: 1057604 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6209. Min Act: -0.0002

Data Index: 617376 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6209. Min Act: -0.0002

Data Index: 362253 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6209. Min Act: -0.0002

Data Index: 832932 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6209. Min Act: -0.0002

Data Index: 535639 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6209. Min Act: -0.0002

Data Index: 1284888 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6124. Min Act: -0.0003

Data Index: 1299497 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6068. Min Act: -0.0002

Data Index: 588047 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6128. Min Act: -0.0002

Data Index: 1526469 (Python Code)

Max Activating Token Index: 793

Text #15

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5907. Min Act: -0.0003

Data Index: 1219825 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5903. Min Act: -0.0002

Data Index: 750408 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5916. Min Act: -0.0003

Data Index: 583673 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5842. Min Act: -0.0002

Data Index: 243942 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5917. Min Act: -0.0003

Data Index: 1091712 (C4 (Web Text))

Max Activating Token Index: 408