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

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

Neuron 4925 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2157. Min Range: -1.2157

Max Act: 1.2157. Min Act: -0.0000

Data Index: 752766 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.2157. Min Range: -1.2157

Max Act: 1.0963. Min Act: -0.0000

Data Index: 276232 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.2157. Min Range: -1.2157

Max Act: 1.0917. Min Act: -0.0000

Data Index: 589407 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.2157. Min Range: -1.2157

Max Act: 1.0220. Min Act: -0.0000

Data Index: 661158 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.9587. Min Act: -0.0000

Data Index: 516102 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.9853. Min Act: -0.0000

Data Index: 592162 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8971. Min Act: -0.0000

Data Index: 40596 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8475. Min Act: -0.0000

Data Index: 233625 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8936. Min Act: -0.0000

Data Index: 417292 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8826. Min Act: -0.0000

Data Index: 802001 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.9053. Min Act: -0.0000

Data Index: 279027 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1310952 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8708. Min Act: -0.0000

Data Index: 367597 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8668. Min Act: -0.0000

Data Index: 943370 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8504. Min Act: -0.0000

Data Index: 644680 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8415. Min Act: -0.0000

Data Index: 290584 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1200750 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1211628 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.8571. Min Act: -0.0000

Data Index: 680039 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 1.2157. Min Range: -1.2157

Max Act: 0.7970. Min Act: -0.0000

Data Index: 96748 (C4 (Web Text))

Max Activating Token Index: 980