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

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

Neuron 3748 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.9798. Min Act: -0.0000

Data Index: 1133879 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 3.0573. Min Range: -3.0573

Max Act: 3.0573. Min Act: -0.0000

Data Index: 172823 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.8562. Min Act: -0.0000

Data Index: 1054094 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.5943. Min Act: -0.0000

Data Index: 549936 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.5636. Min Act: -0.0000

Data Index: 753159 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.2286. Min Act: -0.0000

Data Index: 1199522 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.2133. Min Act: -0.0000

Data Index: 1111120 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.3004. Min Act: -0.0000

Data Index: 318471 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.2783. Min Act: -0.0000

Data Index: 760654 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.2311. Min Act: -0.0000

Data Index: 538187 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.1293. Min Act: -0.0000

Data Index: 822295 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.1162. Min Act: -0.0000

Data Index: 1263759 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.1179. Min Act: -0.0000

Data Index: 780823 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.0815. Min Act: -0.0000

Data Index: 10947 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.1587. Min Act: -0.0000

Data Index: 587063 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.0159. Min Act: -0.0000

Data Index: 27194 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.1112. Min Act: -0.0000

Data Index: 599131 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 3.0573. Min Range: -3.0573

Max Act: 1.9917. Min Act: -0.0000

Data Index: 642428 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.1025. Min Act: -0.0000

Data Index: 832457 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.0573. Min Range: -3.0573

Max Act: 2.0775. Min Act: -0.0000

Data Index: 805871 (C4 (Web Text))

Max Activating Token Index: 85