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

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

Neuron 3693 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8179. Min Range: -5.8179

Max Act: 5.8179. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 5.8179. Min Range: -5.8179

Max Act: 3.7326. Min Act: -0.0002

Data Index: 691412 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 5.8179. Min Range: -5.8179

Max Act: 3.5743. Min Act: -0.0002

Data Index: 211359 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.8502. Min Act: -0.0002

Data Index: 294175 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.4869. Min Act: -0.0002

Data Index: 575848 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.5426. Min Act: -0.0002

Data Index: 425118 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.3277. Min Act: -0.0002

Data Index: 686054 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.3160. Min Act: -0.0001

Data Index: 26692 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.3053. Min Act: -0.0002

Data Index: 207153 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.2436. Min Act: 0.0007

Data Index: 1157597 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.2381. Min Act: -0.0002

Data Index: 1193904 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.2617. Min Act: -0.0002

Data Index: 1246011 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.2027. Min Act: -0.0002

Data Index: 895756 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.1889. Min Act: -0.0001

Data Index: 797303 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.0552. Min Act: -0.0001

Data Index: 95445 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.0477. Min Act: -0.0002

Data Index: 129573 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 5.8179. Min Range: -5.8179

Max Act: 1.9935. Min Act: -0.0002

Data Index: 525683 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 5.8179. Min Range: -5.8179

Max Act: 1.9665. Min Act: -0.0002

Data Index: 539784 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 5.8179. Min Range: -5.8179

Max Act: 2.0121. Min Act: -0.0002

Data Index: 1005617 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 5.8179. Min Range: -5.8179

Max Act: 1.9811. Min Act: -0.0001

Data Index: 781849 (C4 (Web Text))

Max Activating Token Index: 448