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

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

Neuron 988 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.8312. Min Act: -0.0000

Data Index: 770429 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1140379 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.3466. Min Act: -0.0000

Data Index: 218293 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.3106. Min Act: -0.0000

Data Index: 830890 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.2060. Min Act: -0.0000

Data Index: 492797 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.3062. Min Act: -0.0000

Data Index: 78772 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.3052. Min Act: -0.0001

Data Index: 672887 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.2327. Min Act: -0.0000

Data Index: 394951 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.1291. Min Act: -0.0000

Data Index: 43972 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.2955. Min Act: -0.0000

Data Index: 995399 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.2070. Min Act: -0.0000

Data Index: 519746 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.1664. Min Act: -0.0000

Data Index: 344125 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.1705. Min Act: -0.0000

Data Index: 1145128 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.1124. Min Act: -0.0000

Data Index: 530420 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.1457. Min Act: -0.0000

Data Index: 968931 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.1511. Min Act: -0.0000

Data Index: 944514 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1297435 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.8312. Min Range: -1.8312

Max Act: 0.9742. Min Act: -0.0000

Data Index: 552397 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.0434. Min Act: -0.0000

Data Index: 282826 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 1.8312. Min Range: -1.8312

Max Act: 1.0303. Min Act: -0.0000

Data Index: 137768 (C4 (Web Text))

Max Activating Token Index: 776