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

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

Neuron 2322 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.5767. Min Act: -0.0001

Data Index: 1088053 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4984. Min Act: -0.0001

Data Index: 181600 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4644. Min Act: -0.0001

Data Index: 380091 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4460. Min Act: -0.0001

Data Index: 708978 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1128755 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4815. Min Act: -0.0001

Data Index: 519366 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4586. Min Act: -0.0001

Data Index: 1030432 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4329. Min Act: -0.0001

Data Index: 108216 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1259043 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4040. Min Act: -0.0001

Data Index: 214304 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3775. Min Act: -0.0001

Data Index: 1143345 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3755. Min Act: -0.0001

Data Index: 1341994 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3738. Min Act: -0.0001

Data Index: 1016774 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.4007. Min Act: -0.0001

Data Index: 365133 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3718. Min Act: -0.0001

Data Index: 1318470 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3741. Min Act: -0.0001

Data Index: 976418 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3459. Min Act: -0.0001

Data Index: 266090 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3460. Min Act: -0.0001

Data Index: 1185065 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3373. Min Act: -0.0001

Data Index: 389673 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.5767. Min Range: -0.5767

Max Act: 0.3584. Min Act: -0.0001

Data Index: 985069 (C4 (Web Text))

Max Activating Token Index: 206