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

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

Neuron 189 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: 2.2552. Min Range: -2.2552

Max Act: 2.2552. Min Act: -0.0000

Data Index: 454670 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8070. Min Act: -0.0000

Data Index: 334427 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1083484 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1016055 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.7785. Min Act: -0.0000

Data Index: 665001 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.7262. Min Act: -0.0000

Data Index: 1122418 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8639. Min Act: -0.0000

Data Index: 468509 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1087003 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.6521. Min Act: -0.0000

Data Index: 892989 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.6020. Min Act: -0.0000

Data Index: 646054 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.5952. Min Act: -0.0000

Data Index: 44852 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.6243. Min Act: -0.0000

Data Index: 927743 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.5428. Min Act: -0.0000

Data Index: 565368 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.5277. Min Act: -0.0000

Data Index: 356116 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.5189. Min Act: -0.0000

Data Index: 717218 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.4050. Min Act: -0.0000

Data Index: 99024 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.4073. Min Act: -0.0000

Data Index: 1093384 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1049651 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1172596 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.4712. Min Act: -0.0000

Data Index: 406787 (C4 (Web Text))

Max Activating Token Index: 244