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

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

Neuron 2134 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4534. Min Range: -3.4534

Max Act: 3.4534. Min Act: -0.0000

Data Index: 1571839 (Python Code)

Max Activating Token Index: 692

Text #1

Max Range: 3.4534. Min Range: -3.4534

Max Act: 3.2533. Min Act: -0.0000

Data Index: 1436574 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.6280. Min Act: -0.0000

Data Index: 224737 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.8575. Min Act: -0.0000

Data Index: 1045913 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4918. Min Act: -0.0000

Data Index: 1129933 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.6168. Min Act: -0.0000

Data Index: 620020 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.6000. Min Act: -0.0000

Data Index: 510119 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4734. Min Act: -0.0000

Data Index: 770909 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4561. Min Act: -0.0000

Data Index: 1196870 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.5651. Min Act: -0.0000

Data Index: 1420267 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.6956. Min Act: -0.0000

Data Index: 261126 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.5573. Min Act: -0.0000

Data Index: 1165518 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4361. Min Act: -0.0000

Data Index: 1597067 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4145. Min Act: -0.0000

Data Index: 303123 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.5206. Min Act: -0.0000

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.2460. Min Act: -0.0000

Data Index: 283170 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4818. Min Act: -0.0000

Data Index: 1055100 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4754. Min Act: -0.0000

Data Index: 1081929 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.3529. Min Act: -0.0000

Data Index: 553459 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.4534. Min Range: -3.4534

Max Act: 2.4789. Min Act: -0.0000

Data Index: 1392068 (Python Code)

Max Activating Token Index: 492