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

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

Neuron 4126 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4612. Min Act: -0.0000

Data Index: 929353 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4840. Min Act: -0.0000

Data Index: 913724 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4428. Min Act: -0.0000

Data Index: 83645 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1173130 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1279034 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4196. Min Act: -0.0000

Data Index: 755226 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3942. Min Act: -0.0000

Data Index: 143956 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4151. Min Act: -0.0000

Data Index: 889866 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1110084 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4072. Min Act: -0.0000

Data Index: 599368 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3885. Min Act: -0.0000

Data Index: 820429 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3847. Min Act: -0.0000

Data Index: 618437 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3936. Min Act: -0.0000

Data Index: 137093 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1589930 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3671. Min Act: -0.0000

Data Index: 945117 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1389926 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3697. Min Act: -0.0000

Data Index: 275488 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3934. Min Act: -0.0000

Data Index: 58105 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3888. Min Act: -0.0000

Data Index: 452777 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1188955 (C4 (Web Text))

Max Activating Token Index: 792