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

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

Neuron 923 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: 4.5742. Min Range: -4.5742

Max Act: 4.5179. Min Act: -0.0000

Data Index: 49604 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.5742. Min Act: -0.0000

Data Index: 1224268 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.3440. Min Act: -0.0000

Data Index: 460266 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.1594. Min Act: -0.0000

Data Index: 142701 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.1718. Min Act: -0.0000

Data Index: 298309 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.9437. Min Act: -0.0000

Data Index: 1073201 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.8874. Min Act: -0.0000

Data Index: 1099964 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.8314. Min Act: -0.0000

Data Index: 1095155 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.1277. Min Act: -0.0000

Data Index: 522612 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.1369. Min Act: -0.0000

Data Index: 1242676 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.0966. Min Act: -0.0000

Data Index: 1099951 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.0952. Min Act: -0.0000

Data Index: 578844 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.7483. Min Act: -0.0000

Data Index: 1240890 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.8879. Min Act: -0.0000

Data Index: 558029 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.8803. Min Act: -0.0000

Data Index: 250028 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.5499. Min Act: -0.0000

Data Index: 360844 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 4.5742. Min Range: -4.5742

Max Act: 4.0672. Min Act: -0.0000

Data Index: 700896 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.8437. Min Act: -0.0000

Data Index: 517020 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.8400. Min Act: -0.0000

Data Index: 552196 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 4.5742. Min Range: -4.5742

Max Act: 3.6832. Min Act: -0.0000

Data Index: 1006115 (C4 (Web Text))

Max Activating Token Index: 739