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

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

Neuron 4038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.8239. Min Act: -0.0000

Data Index: 188678 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1051286 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.6703. Min Act: -0.0000

Data Index: 155600 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1008285 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.6835. Min Act: -0.0000

Data Index: 522857 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.7718. Min Act: -0.0000

Data Index: 293529 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1143215 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5954. Min Act: -0.0000

Data Index: 357630 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5451. Min Act: -0.0000

Data Index: 167356 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.4776. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1249885 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5183. Min Act: -0.0000

Data Index: 64577 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1298952 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.6939. Min Act: -0.0000

Data Index: 767296 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.4673. Min Act: -0.0000

Data Index: 502285 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5522. Min Act: -0.0000

Data Index: 174288 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.4137. Min Act: -0.0000

Data Index: 98713 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1575874 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.5785. Min Act: -0.0000

Data Index: 603940 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.8239. Min Range: -1.8239

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1313343 (C4 (Web Text))

Max Activating Token Index: 270