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

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

Neuron 2157 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0793. Min Range: -7.0793

Max Act: 7.0126. Min Act: -0.0001

Data Index: 417776 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.9634. Min Act: -0.0001

Data Index: 749065 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.8059. Min Act: -0.0001

Data Index: 248486 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 7.0793. Min Range: -7.0793

Max Act: 7.0793. Min Act: -0.0001

Data Index: 489695 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.4556. Min Act: -0.0001

Data Index: 480128 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.2486. Min Act: -0.0001

Data Index: 216434 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.8430. Min Act: -0.0001

Data Index: 34214 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.1319. Min Act: -0.0001

Data Index: 218497 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.7863. Min Act: -0.0001

Data Index: 325322 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.9213. Min Act: -0.0001

Data Index: 1063455 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.0054. Min Act: -0.0001

Data Index: 1016785 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.6509. Min Act: -0.0001

Data Index: 252482 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.6291. Min Act: -0.0001

Data Index: 982496 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.9994. Min Act: -0.0001

Data Index: 880327 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.8875. Min Act: -0.0001

Data Index: 860076 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.8608. Min Act: -0.0001

Data Index: 676574 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 7.0793. Min Range: -7.0793

Max Act: 6.0147. Min Act: -0.0001

Data Index: 258248 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.7976. Min Act: -0.0001

Data Index: 218802 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.8947. Min Act: -0.0001

Data Index: 1461226 (Python Code)

Max Activating Token Index: 932

Text #19

Max Range: 7.0793. Min Range: -7.0793

Max Act: 5.7500. Min Act: -0.0001

Data Index: 598031 (C4 (Web Text))

Max Activating Token Index: 387