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

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

Neuron 2404 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1563114 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1478262 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1626161 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1031940 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4759. Min Act: -0.0000

Data Index: 677238 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1656954 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4562. Min Act: -0.0000

Data Index: 359232 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4578. Min Act: -0.0000

Data Index: 531836 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1547688 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4594. Min Act: -0.0000

Data Index: 246583 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4477. Min Act: -0.0000

Data Index: 180542 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4119. Min Act: -0.0000

Data Index: 683286 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4408. Min Act: -0.0000

Data Index: 288655 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4205. Min Act: -0.0000

Data Index: 529054 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1375680 (Python Code)

Max Activating Token Index: 59

Text #15

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3952. Min Act: -0.0000

Data Index: 824565 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4365. Min Act: -0.0000

Data Index: 578189 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4439. Min Act: -0.0000

Data Index: 605975 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1429437 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3929. Min Act: -0.0000

Data Index: 845563 (C4 (Web Text))

Max Activating Token Index: 140