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

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

Neuron 5466 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3929. Min Range: -2.3929

Max Act: 2.3929. Min Act: -0.0000

Data Index: 1062138 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 2.3929. Min Range: -2.3929

Max Act: 2.2602. Min Act: -0.0000

Data Index: 680169 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 2.3929. Min Range: -2.3929

Max Act: 2.2133. Min Act: -0.0000

Data Index: 1300833 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 2.3929. Min Range: -2.3929

Max Act: 2.0583. Min Act: -0.0000

Data Index: 1568757 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9560. Min Act: -0.0000

Data Index: 27859 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.3929. Min Range: -2.3929

Max Act: 2.0035. Min Act: -0.0000

Data Index: 733196 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9636. Min Act: -0.0000

Data Index: 32614 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9976. Min Act: -0.0000

Data Index: 799012 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9475. Min Act: -0.0000

Data Index: 9732 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8271. Min Act: -0.0000

Data Index: 916628 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8235. Min Act: -0.0000

Data Index: 500689 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8166. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9136. Min Act: -0.0000

Data Index: 535989 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9018. Min Act: -0.0000

Data Index: 374584 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9070. Min Act: -0.0000

Data Index: 1505032 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8946. Min Act: -0.0000

Data Index: 1263297 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8867. Min Act: -0.0000

Data Index: 277829 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8560. Min Act: -0.0000

Data Index: 183651 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.9593. Min Act: -0.0000

Data Index: 1382935 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 2.3929. Min Range: -2.3929

Max Act: 1.8335. Min Act: -0.0000

Data Index: 612842 (C4 (Web Text))

Max Activating Token Index: 907