Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1463 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.5100. Min Act: -0.0001

Data Index: 573130 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3928. Min Act: -0.0001

Data Index: 1006870 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3046. Min Act: -0.0001

Data Index: 1116455 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.4739. Min Act: -0.0001

Data Index: 764376 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.4090. Min Act: -0.0001

Data Index: 484353 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2793. Min Act: -0.0001

Data Index: 583312 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2786. Min Act: -0.0001

Data Index: 1128169 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3760. Min Act: -0.0001

Data Index: 135958 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2688. Min Act: -0.0001

Data Index: 58732 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.4705. Min Act: -0.0001

Data Index: 213643 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2816. Min Act: -0.0001

Data Index: 383129 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3606. Min Act: -0.0001

Data Index: 925119 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2785. Min Act: -0.0001

Data Index: 839470 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2421. Min Act: -0.0001

Data Index: 857986 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.5003. Min Act: -0.0001

Data Index: 468303 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.3096. Min Act: -0.0001

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2494. Min Act: -0.0001

Data Index: 1347723 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2232. Min Act: -0.0001

Data Index: 1023997 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2485. Min Act: -0.0001

Data Index: 527339 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 1.5100. Min Range: -1.5100

Max Act: 1.2862. Min Act: -0.0001

Data Index: 1274154 (C4 (Web Text))

Max Activating Token Index: 1003