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

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

Neuron 2414 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4794. Min Act: -0.0000

Data Index: 636146 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4455. Min Act: -0.0000

Data Index: 710586 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4123. Min Act: -0.0000

Data Index: 732351 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.4292. Min Act: -0.0000

Data Index: 306840 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3592. Min Act: -0.0000

Data Index: 507513 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1051407 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3744. Min Act: -0.0000

Data Index: 705334 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3585. Min Act: -0.0000

Data Index: 170972 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3349. Min Act: -0.0000

Data Index: 486143 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3424. Min Act: -0.0000

Data Index: 550201 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3194. Min Act: -0.0000

Data Index: 105832 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3026. Min Act: -0.0000

Data Index: 4187 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3108. Min Act: -0.0000

Data Index: 945314 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3028. Min Act: -0.0000

Data Index: 794512 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3063. Min Act: -0.0000

Data Index: 13600 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3126. Min Act: -0.0000

Data Index: 648969 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.3029. Min Act: -0.0000

Data Index: 733136 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2815. Min Act: -0.0000

Data Index: 122881 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2597. Min Act: -0.0000

Data Index: 409241 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.4794. Min Range: -0.4794

Max Act: 0.2888. Min Act: -0.0000

Data Index: 545977 (C4 (Web Text))

Max Activating Token Index: 693