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

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

Neuron 5824 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: 1.9032. Min Range: -1.9032

Max Act: 1.9032. Min Act: -0.0000

Data Index: 734651 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.7916. Min Act: -0.0000

Data Index: 506272 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.6258. Min Act: -0.0000

Data Index: 478774 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.6576. Min Act: -0.0000

Data Index: 252419 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.6338. Min Act: -0.0000

Data Index: 849112 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.5119. Min Act: -0.0000

Data Index: 142867 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.5590. Min Act: -0.0000

Data Index: 312508 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.3954. Min Act: -0.0000

Data Index: 734165 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.4974. Min Act: -0.0000

Data Index: 398951 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.4066. Min Act: -0.0000

Data Index: 186965 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.4712. Min Act: -0.0000

Data Index: 784899 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.3755. Min Act: -0.0000

Data Index: 1007179 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.3666. Min Act: -0.0000

Data Index: 17811 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.4418. Min Act: -0.0000

Data Index: 872001 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.3114. Min Act: -0.0000

Data Index: 162616 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.2980. Min Act: -0.0000

Data Index: 564396 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.2948. Min Act: -0.0000

Data Index: 564279 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1118091 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.9032. Min Range: -1.9032

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1136873 (C4 (Web Text))

Max Activating Token Index: 806