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

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

Neuron 2970 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2467. Min Range: -4.2467

Max Act: 4.2467. Min Act: -0.0000

Data Index: 156106 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 4.2467. Min Range: -4.2467

Max Act: 4.1884. Min Act: -0.0000

Data Index: 1098730 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.8158. Min Act: -0.0000

Data Index: 433533 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4562. Min Act: -0.0000

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.5807. Min Act: -0.0000

Data Index: 1017598 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.7281. Min Act: -0.0000

Data Index: 392795 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.7182. Min Act: -0.0000

Data Index: 205151 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.5972. Min Act: -0.0000

Data Index: 424824 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.5752. Min Act: -0.0000

Data Index: 1001022 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4045. Min Act: -0.0000

Data Index: 1039788 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4864. Min Act: -0.0000

Data Index: 28061 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4518. Min Act: -0.0000

Data Index: 925227 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.3373. Min Act: -0.0000

Data Index: 484735 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4776. Min Act: -0.0000

Data Index: 1124150 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4770. Min Act: -0.0000

Data Index: 1188827 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.5953. Min Act: -0.0000

Data Index: 463014 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4757. Min Act: -0.0000

Data Index: 721050 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4591. Min Act: -0.0000

Data Index: 86584 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4558. Min Act: -0.0000

Data Index: 966176 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 4.2467. Min Range: -4.2467

Max Act: 3.4910. Min Act: -0.0000

Data Index: 436431 (C4 (Web Text))

Max Activating Token Index: 352