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

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

Neuron 4893 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3142. Min Range: -1.3142

Max Act: 1.3142. Min Act: -0.0000

Data Index: 489099 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.3142. Min Range: -1.3142

Max Act: 1.0655. Min Act: -0.0000

Data Index: 659333 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8974. Min Act: -0.0000

Data Index: 715082 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.9616. Min Act: -0.0000

Data Index: 902674 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.9823. Min Act: -0.0000

Data Index: 953217 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.3142. Min Range: -1.3142

Max Act: 1.1056. Min Act: -0.0000

Data Index: 268890 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.9740. Min Act: -0.0000

Data Index: 158241 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.9057. Min Act: -0.0000

Data Index: 136088 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8684. Min Act: -0.0000

Data Index: 450740 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8648. Min Act: -0.0000

Data Index: 256575 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.9016. Min Act: -0.0000

Data Index: 993879 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8178. Min Act: -0.0000

Data Index: 594145 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8138. Min Act: -0.0000

Data Index: 506669 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8069. Min Act: -0.0000

Data Index: 544873 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8072. Min Act: -0.0000

Data Index: 124606 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8207. Min Act: -0.0000

Data Index: 415961 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.7741. Min Act: -0.0000

Data Index: 139545 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.8199. Min Act: -0.0000

Data Index: 953091 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.7474. Min Act: -0.0000

Data Index: 714884 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.3142. Min Range: -1.3142

Max Act: 0.7449. Min Act: -0.0000

Data Index: 377106 (C4 (Web Text))

Max Activating Token Index: 195