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

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

Neuron 4744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4880. Min Act: -0.0000

Data Index: 617074 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.3106. Min Act: -0.0000

Data Index: 1254373 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4072. Min Act: -0.0000

Data Index: 437581 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.4220. Min Act: -0.0000

Data Index: 712217 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.2355. Min Act: -0.0000

Data Index: 1125561 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1861. Min Act: -0.0000

Data Index: 459280 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.2147. Min Act: -0.0000

Data Index: 216109 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.0952. Min Act: -0.0000

Data Index: 1049418 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8710. Min Act: -0.0000

Data Index: 550826 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8857. Min Act: -0.0000

Data Index: 661890 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8745. Min Act: -0.0000

Data Index: 1108646 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9735. Min Act: -0.0000

Data Index: 547510 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.4880. Min Range: -3.4880

Max Act: 3.1014. Min Act: -0.0000

Data Index: 74352 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9416. Min Act: -0.0000

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9180. Min Act: -0.0000

Data Index: 994947 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8353. Min Act: -0.0000

Data Index: 204287 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.8237. Min Act: -0.0000

Data Index: 223965 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.7846. Min Act: -0.0000

Data Index: 128019 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.6434. Min Act: -0.0000

Data Index: 929260 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 3.4880. Min Range: -3.4880

Max Act: 2.9048. Min Act: -0.0000

Data Index: 82161 (C4 (Web Text))

Max Activating Token Index: 719