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

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

Neuron 1559 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: 5.4769. Min Range: -5.4769

Max Act: 5.4769. Min Act: -0.0000

Data Index: 1336722 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 5.4769. Min Range: -5.4769

Max Act: 4.6882. Min Act: -0.0000

Data Index: 352196 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 5.4769. Min Range: -5.4769

Max Act: 4.9918. Min Act: -0.0000

Data Index: 1135876 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 5.4769. Min Range: -5.4769

Max Act: 4.5362. Min Act: -0.0000

Data Index: 282972 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 5.4769. Min Range: -5.4769

Max Act: 4.2959. Min Act: -0.0000

Data Index: 529662 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.8850. Min Act: -0.0000

Data Index: 117577 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 5.4769. Min Range: -5.4769

Max Act: 4.0364. Min Act: 0.0000

Data Index: 555741 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.8144. Min Act: -0.0000

Data Index: 1107898 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.9022. Min Act: -0.0000

Data Index: 995147 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.8636. Min Act: 0.0000

Data Index: 26560 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.6828. Min Act: -0.0000

Data Index: 759911 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.7838. Min Act: -0.0000

Data Index: 250963 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.4045. Min Act: 0.0000

Data Index: 13633 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.5176. Min Act: -0.0000

Data Index: 145945 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.5309. Min Act: -0.0000

Data Index: 828946 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.4984. Min Act: -0.0000

Data Index: 614370 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.5053. Min Act: -0.0000

Data Index: 398256 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.4436. Min Act: -0.0000

Data Index: 686030 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.2886. Min Act: -0.0000

Data Index: 1102364 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 5.4769. Min Range: -5.4769

Max Act: 3.7177. Min Act: -0.0000

Data Index: 263881 (C4 (Web Text))

Max Activating Token Index: 183