Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1082 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1247051 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 1.0895. Min Range: -1.0895

Max Act: 1.0895. Min Act: -0.0000

Data Index: 863606 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 1.0895. Min Range: -1.0895

Max Act: 1.0036. Min Act: -0.0000

Data Index: 982559 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.0895. Min Range: -1.0895

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1106767 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 1.0895. Min Range: -1.0895

Max Act: 1.0297. Min Act: -0.0000

Data Index: 568619 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.0895. Min Range: -1.0895

Max Act: 1.0099. Min Act: -0.0000

Data Index: 246860 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8808. Min Act: -0.0000

Data Index: 415533 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1186439 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1211113 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.9393. Min Act: -0.0000

Data Index: 721476 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8451. Min Act: -0.0000

Data Index: 278726 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1276463 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8153. Min Act: -0.0000

Data Index: 241558 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.7884. Min Act: -0.0000

Data Index: 144352 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8105. Min Act: -0.0000

Data Index: 361799 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.7839. Min Act: -0.0000

Data Index: 945709 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1252012 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.5821. Min Act: -0.0000

Data Index: 434769 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1358031 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.0895. Min Range: -1.0895

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1063910 (C4 (Web Text))

Max Activating Token Index: 982