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

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

Neuron 6122 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0137. Min Range: -5.0137

Max Act: 5.0137. Min Act: -0.0000

Data Index: 1323705 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.1153. Min Act: -0.0000

Data Index: 439821 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.7985. Min Act: -0.0000

Data Index: 991562 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.8282. Min Act: -0.0000

Data Index: 1087518 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.4627. Min Act: -0.0000

Data Index: 600805 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.5621. Min Act: -0.0000

Data Index: 1565631 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.4353. Min Act: -0.0000

Data Index: 903177 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.4213. Min Act: -0.0000

Data Index: 1290635 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.4973. Min Act: -0.0000

Data Index: 1565070 (Python Code)

Max Activating Token Index: 933

Text #9

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.3051. Min Act: -0.0000

Data Index: 615375 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.2924. Min Act: -0.0000

Data Index: 1594680 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.1763. Min Act: -0.0000

Data Index: 956373 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 5.0137. Min Range: -5.0137

Max Act: 2.9870. Min Act: -0.0000

Data Index: 1108168 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 5.0137. Min Range: -5.0137

Max Act: 2.9809. Min Act: -0.0000

Data Index: 446152 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.0968. Min Act: -0.0000

Data Index: 1096701 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.0813. Min Act: -0.0000

Data Index: 273721 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.0825. Min Act: -0.0000

Data Index: 1446190 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 5.0137. Min Range: -5.0137

Max Act: 2.9119. Min Act: -0.0000

Data Index: 1382829 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 5.0137. Min Range: -5.0137

Max Act: 3.0283. Min Act: -0.0000

Data Index: 1617952 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 5.0137. Min Range: -5.0137

Max Act: 2.9920. Min Act: -0.0000

Data Index: 885073 (C4 (Web Text))

Max Activating Token Index: 787