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

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

Neuron 2009 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1497128 (Python Code)

Max Activating Token Index: 126

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1185187 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0973. Min Act: -0.0001

Data Index: 197315 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1133487 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1604696 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0818. Min Act: -0.0001

Data Index: 709973 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1014552 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0792. Min Act: -0.0001

Data Index: 81097 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0851. Min Act: -0.0001

Data Index: 11309 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0812. Min Act: -0.0001

Data Index: 53052 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0755. Min Act: -0.0001

Data Index: 240146 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0751. Min Act: -0.0001

Data Index: 919428 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0731. Min Act: -0.0001

Data Index: 854646 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0752. Min Act: -0.0001

Data Index: 429571 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0771. Min Act: -0.0001

Data Index: 747398 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1025658 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0661. Min Act: -0.0001

Data Index: 707073 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0764. Min Act: -0.0001

Data Index: 189917 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1247762 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1201989 (C4 (Web Text))

Max Activating Token Index: 179