Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3346 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1552356 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1416898 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1633543 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1396650 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1629771 (Python Code)

Max Activating Token Index: 130

Text #5

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1466770 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1576018 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1645909 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1362750 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1601022 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1645663 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1478579 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3668. Min Act: -0.0000

Data Index: 414176 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1645871 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1390045 (Python Code)

Max Activating Token Index: 349

Text #15

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1569978 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1550827 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1443058 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1628325 (Python Code)

Max Activating Token Index: 258

Text #19

Max Range: 0.4771. Min Range: -0.4771

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1625043 (Python Code)

Max Activating Token Index: 355