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

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

Neuron 5112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.5221. Min Act: -0.0000

Data Index: 118301 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.2342. Min Act: -0.0000

Data Index: 867704 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.2477. Min Act: -0.0000

Data Index: 459860 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.0960. Min Act: -0.0000

Data Index: 25499 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.0984. Min Act: -0.0000

Data Index: 379487 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.0749. Min Act: -0.0000

Data Index: 450483 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.0583. Min Act: -0.0000

Data Index: 767401 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.9935. Min Act: -0.0000

Data Index: 53978 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.9739. Min Act: -0.0000

Data Index: 119980 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.9494. Min Act: -0.0000

Data Index: 1089670 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.0786. Min Act: -0.0000

Data Index: 276798 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.7738. Min Act: -0.0000

Data Index: 635190 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.9415. Min Act: -0.0000

Data Index: 832698 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.9044. Min Act: -0.0000

Data Index: 860331 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 3.5221. Min Range: -3.5221

Max Act: 3.0123. Min Act: -0.0000

Data Index: 253087 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.5486. Min Act: -0.0000

Data Index: 789575 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.8491. Min Act: -0.0000

Data Index: 202179 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.9694. Min Act: -0.0000

Data Index: 625755 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.8364. Min Act: -0.0000

Data Index: 574665 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 3.5221. Min Range: -3.5221

Max Act: 2.5686. Min Act: -0.0000

Data Index: 1040335 (C4 (Web Text))

Max Activating Token Index: 836