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

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

Neuron 199 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5784. Min Range: -3.5784

Max Act: 3.5784. Min Act: -0.0000

Data Index: 1172292 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.5784. Min Range: -3.5784

Max Act: 3.3984. Min Act: -0.0000

Data Index: 1052056 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.5784. Min Range: -3.5784

Max Act: 3.1758. Min Act: -0.0000

Data Index: 108581 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 3.5784. Min Range: -3.5784

Max Act: 3.2498. Min Act: -0.0000

Data Index: 934883 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.8972. Min Act: -0.0000

Data Index: 1130179 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.8782. Min Act: -0.0000

Data Index: 528012 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.8650. Min Act: 0.0000

Data Index: 1205662 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.6900. Min Act: -0.0000

Data Index: 102625 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.8057. Min Act: -0.0000

Data Index: 1329762 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.6535. Min Act: -0.0000

Data Index: 285894 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.7566. Min Act: -0.0000

Data Index: 937031 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.4626. Min Act: -0.0000

Data Index: 878641 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.1991. Min Act: -0.0000

Data Index: 982394 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.4451. Min Act: -0.0000

Data Index: 241004 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.4462. Min Act: -0.0000

Data Index: 1075640 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.5187. Min Act: -0.0000

Data Index: 123551 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.1585. Min Act: -0.0000

Data Index: 328529 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.3194. Min Act: 0.0000

Data Index: 288486 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1209148 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 3.5784. Min Range: -3.5784

Max Act: 2.1877. Min Act: -0.0000

Data Index: 278218 (C4 (Web Text))

Max Activating Token Index: 659