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

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

Neuron 861 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: 4.7892. Min Range: -4.7892

Max Act: 4.7892. Min Act: -0.0000

Data Index: 1079543 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 4.7892. Min Range: -4.7892

Max Act: 4.7063. Min Act: -0.0000

Data Index: 1253153 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 4.7892. Min Range: -4.7892

Max Act: 4.6875. Min Act: -0.0000

Data Index: 398097 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 4.7892. Min Range: -4.7892

Max Act: 4.3126. Min Act: -0.0000

Data Index: 849203 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.8219. Min Act: -0.0000

Data Index: 1289436 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.5903. Min Act: -0.0000

Data Index: 742229 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.2331. Min Act: -0.0000

Data Index: 557502 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.3392. Min Act: -0.0000

Data Index: 113578 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.6924. Min Act: -0.0000

Data Index: 184148 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 4.7892. Min Range: -4.7892

Max Act: 2.7479. Min Act: -0.0000

Data Index: 1339373 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.0975. Min Act: -0.0000

Data Index: 863917 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.3784. Min Act: -0.0000

Data Index: 838003 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.0946. Min Act: -0.0000

Data Index: 1073317 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.3427. Min Act: -0.0001

Data Index: 1002375 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.3309. Min Act: -0.0001

Data Index: 69545 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.3387. Min Act: -0.0000

Data Index: 835957 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 4.7892. Min Range: -4.7892

Max Act: 4.4240. Min Act: -0.0000

Data Index: 1288474 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.6015. Min Act: -0.0000

Data Index: 1090005 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.1242. Min Act: -0.0000

Data Index: 1162827 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 4.7892. Min Range: -4.7892

Max Act: 3.6679. Min Act: -0.0000

Data Index: 339217 (C4 (Web Text))

Max Activating Token Index: 768