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

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

Neuron 3789 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: 0.4906. Min Range: -0.4906

Max Act: 0.4906. Min Act: -0.0000

Data Index: 514393 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.4504. Min Act: 0.0000

Data Index: 1205747 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1242576 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1423160 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3324. Min Act: -0.0000

Data Index: 573396 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3209. Min Act: -0.0000

Data Index: 419764 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3064. Min Act: -0.0000

Data Index: 685817 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1329977 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2992. Min Act: -0.0000

Data Index: 373033 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2918. Min Act: -0.0000

Data Index: 843249 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3053. Min Act: -0.0000

Data Index: 402718 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.3069. Min Act: -0.0000

Data Index: 567934 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2886. Min Act: -0.0000

Data Index: 990324 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1639541 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2868. Min Act: -0.0000

Data Index: 177719 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2896. Min Act: -0.0000

Data Index: 691497 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2725. Min Act: -0.0000

Data Index: 235090 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2762. Min Act: -0.0000

Data Index: 514132 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2691. Min Act: -0.0000

Data Index: 763375 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.4906. Min Range: -0.4906

Max Act: 0.2735. Min Act: -0.0000

Data Index: 498334 (C4 (Web Text))

Max Activating Token Index: 73