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

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

Neuron 1651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1166631 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1250432 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2593. Min Act: -0.0000

Data Index: 826910 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2504. Min Act: -0.0000

Data Index: 928582 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2466. Min Act: -0.0000

Data Index: 996007 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2356. Min Act: -0.0000

Data Index: 364349 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2520. Min Act: -0.0000

Data Index: 948077 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2454. Min Act: -0.0000

Data Index: 963784 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2211. Min Act: -0.0000

Data Index: 691887 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2236. Min Act: -0.0000

Data Index: 145703 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2328. Min Act: -0.0000

Data Index: 683273 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2193. Min Act: -0.0000

Data Index: 159450 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2228. Min Act: -0.0000

Data Index: 199296 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2355. Min Act: -0.0000

Data Index: 670239 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2210. Min Act: -0.0000

Data Index: 691195 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1205039 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1215034 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1909. Min Act: -0.0000

Data Index: 68899 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1003923 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1839. Min Act: -0.0000

Data Index: 77389 (C4 (Web Text))

Max Activating Token Index: 611