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

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

Neuron 892 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3878. Min Range: -3.3878

Max Act: 3.3878. Min Act: -0.0001

Data Index: 399871 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.9138. Min Act: -0.0001

Data Index: 1087507 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.5126. Min Act: -0.0000

Data Index: 619331 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.8353. Min Act: -0.0000

Data Index: 1083610 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.7800. Min Act: -0.0000

Data Index: 1149316 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.9169. Min Act: -0.0000

Data Index: 483121 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.7047. Min Act: -0.0001

Data Index: 318604 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.3102. Min Act: -0.0001

Data Index: 1013100 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.6487. Min Act: -0.0001

Data Index: 1311982 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.6942. Min Act: -0.0001

Data Index: 1203332 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.3766. Min Act: -0.0000

Data Index: 255998 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.4480. Min Act: -0.0000

Data Index: 640457 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.3974. Min Act: -0.0000

Data Index: 1073975 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.4295. Min Act: -0.0000

Data Index: 382099 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.4121. Min Act: -0.0000

Data Index: 214004 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.2844. Min Act: -0.0001

Data Index: 860345 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.4114. Min Act: -0.0000

Data Index: 1298283 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.3989. Min Act: -0.0000

Data Index: 256699 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.3882. Min Act: -0.0001

Data Index: 931828 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 3.3878. Min Range: -3.3878

Max Act: 2.6080. Min Act: -0.0000

Data Index: 1311666 (C4 (Web Text))

Max Activating Token Index: 289