Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 811 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3732. Min Act: -0.0000

Data Index: 652687 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1330457 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3628. Min Act: -0.0001

Data Index: 326052 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3729. Min Act: -0.0000

Data Index: 456290 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1144644 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3161. Min Act: -0.0001

Data Index: 76494 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1354858 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3209. Min Act: -0.0000

Data Index: 438955 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3217. Min Act: -0.0000

Data Index: 986819 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3001. Min Act: -0.0000

Data Index: 503373 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3091. Min Act: -0.0000

Data Index: 89145 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2864. Min Act: -0.0000

Data Index: 574930 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1190118 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2925. Min Act: -0.0001

Data Index: 693266 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2931. Min Act: -0.0000

Data Index: 642346 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2797. Min Act: -0.0000

Data Index: 15019 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1060661 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1356046 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2884. Min Act: -0.0001

Data Index: 180348 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.3795. Min Range: -0.3795

Max Act: 0.2734. Min Act: -0.0000

Data Index: 770979 (C4 (Web Text))

Max Activating Token Index: 807