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

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

Neuron 3867 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: 3.4432. Min Range: -3.4432

Max Act: 3.4432. Min Act: -0.0000

Data Index: 366560 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 3.4432. Min Range: -3.4432

Max Act: 3.0347. Min Act: -0.0000

Data Index: 922029 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.4395. Min Act: -0.0000

Data Index: 284713 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.3313. Min Act: -0.0000

Data Index: 1282007 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.2819. Min Act: -0.0001

Data Index: 1298495 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.1934. Min Act: -0.0000

Data Index: 871288 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.8648. Min Act: -0.0000

Data Index: 827794 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.8740. Min Act: -0.0000

Data Index: 615038 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.1646. Min Act: -0.0000

Data Index: 565093 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.0393. Min Act: -0.0001

Data Index: 285557 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.9261. Min Act: -0.0000

Data Index: 920106 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 3.4432. Min Range: -3.4432

Max Act: 2.2161. Min Act: -0.0000

Data Index: 328121 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.7899. Min Act: -0.0000

Data Index: 925271 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.8802. Min Act: -0.0001

Data Index: 1282237 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.6951. Min Act: -0.0000

Data Index: 92827 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.7140. Min Act: -0.0000

Data Index: 924338 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.9041. Min Act: -0.0000

Data Index: 554306 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.5650. Min Act: -0.0000

Data Index: 127979 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1246001 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.4432. Min Range: -3.4432

Max Act: 1.9348. Min Act: -0.0001

Data Index: 923912 (C4 (Web Text))

Max Activating Token Index: 491