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

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

Neuron 60 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: 3.1869. Min Range: -3.1869

Max Act: 3.1869. Min Act: -0.0000

Data Index: 1514347 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 3.1869. Min Range: -3.1869

Max Act: 3.1683. Min Act: -0.0000

Data Index: 1416912 (Python Code)

Max Activating Token Index: 668

Text #2

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.8859. Min Act: -0.0000

Data Index: 575058 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.8593. Min Act: -0.0000

Data Index: 1303426 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.8958. Min Act: -0.0000

Data Index: 1625677 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.7314. Min Act: -0.0000

Data Index: 45551 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.6837. Min Act: -0.0000

Data Index: 619717 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.6209. Min Act: -0.0000

Data Index: 368173 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.5201. Min Act: -0.0000

Data Index: 546363 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.5020. Min Act: -0.0000

Data Index: 1615068 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.6229. Min Act: -0.0000

Data Index: 110179 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.5006. Min Act: -0.0000

Data Index: 557676 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4650. Min Act: -0.0000

Data Index: 1581348 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4414. Min Act: -0.0000

Data Index: 1310066 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.2930. Min Act: -0.0000

Data Index: 1387783 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4043. Min Act: -0.0000

Data Index: 667464 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.4969. Min Act: -0.0000

Data Index: 1468887 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.3728. Min Act: -0.0000

Data Index: 1584098 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1053428 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 3.1869. Min Range: -3.1869

Max Act: 2.2142. Min Act: -0.0000

Data Index: 1525244 (Python Code)

Max Activating Token Index: 901