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

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

Neuron 5096 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4022. Min Range: -7.4022

Max Act: 7.4022. Min Act: -0.0000

Data Index: 995631 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.8520. Min Act: -0.0000

Data Index: 636850 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.7751. Min Act: -0.0000

Data Index: 311596 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.9009. Min Act: -0.0000

Data Index: 998909 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.9795. Min Act: -0.0000

Data Index: 721574 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.0947. Min Act: -0.0000

Data Index: 875508 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.1505. Min Act: -0.0000

Data Index: 783343 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.1665. Min Act: -0.0000

Data Index: 1303787 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.7796. Min Act: -0.0000

Data Index: 1161491 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.5795. Min Act: -0.0000

Data Index: 228013 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.7548. Min Act: -0.0000

Data Index: 718027 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.5573. Min Act: -0.0000

Data Index: 820803 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.4796. Min Act: -0.0000

Data Index: 449036 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.0072. Min Act: -0.0000

Data Index: 179859 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 7.4022. Min Range: -7.4022

Max Act: 6.1922. Min Act: -0.0000

Data Index: 1314704 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.6216. Min Act: -0.0000

Data Index: 1348284 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.3675. Min Act: -0.0000

Data Index: 962702 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.5479. Min Act: -0.0000

Data Index: 287980 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.5179. Min Act: -0.0000

Data Index: 1297013 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 7.4022. Min Range: -7.4022

Max Act: 5.5182. Min Act: -0.0000

Data Index: 434762 (C4 (Web Text))

Max Activating Token Index: 213