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

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

Neuron 2387 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: 0.5968. Min Range: -0.5968

Max Act: 0.5660. Min Act: -0.0000

Data Index: 932487 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1230664 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5870. Min Act: -0.0000

Data Index: 513171 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5607. Min Act: -0.0000

Data Index: 745003 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5428. Min Act: -0.0000

Data Index: 331131 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5202. Min Act: -0.0000

Data Index: 952636 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5075. Min Act: -0.0000

Data Index: 245921 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5267. Min Act: -0.0000

Data Index: 985656 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5206. Min Act: -0.0000

Data Index: 794463 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4707. Min Act: -0.0000

Data Index: 562221 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1308362 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4794. Min Act: -0.0000

Data Index: 457624 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4637. Min Act: -0.0000

Data Index: 877296 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1299890 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1288998 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4671. Min Act: -0.0000

Data Index: 335552 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4617. Min Act: -0.0000

Data Index: 42613 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1111694 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1146747 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4858. Min Act: -0.0000

Data Index: 79811 (C4 (Web Text))

Max Activating Token Index: 709