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

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

Neuron 1091 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0625. Min Range: -4.0625

Max Act: 4.0089. Min Act: -0.0000

Data Index: 1067147 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 4.0625. Min Range: -4.0625

Max Act: 4.0625. Min Act: -0.0000

Data Index: 457963 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.6885. Min Act: -0.0000

Data Index: 1168263 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.7011. Min Act: -0.0000

Data Index: 16380 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.6804. Min Act: -0.0000

Data Index: 545055 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.4459. Min Act: -0.0000

Data Index: 631489 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.3483. Min Act: -0.0000

Data Index: 828522 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.2192. Min Act: -0.0000

Data Index: 1164108 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.1995. Min Act: -0.0000

Data Index: 987631 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.1373. Min Act: -0.0000

Data Index: 488607 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.0889. Min Act: -0.0000

Data Index: 195499 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.2309. Min Act: -0.0000

Data Index: 553861 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.0592. Min Act: -0.0000

Data Index: 830656 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 4.0625. Min Range: -4.0625

Max Act: 2.8977. Min Act: -0.0000

Data Index: 1225883 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 4.0625. Min Range: -4.0625

Max Act: 2.9146. Min Act: -0.0000

Data Index: 736080 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 4.0625. Min Range: -4.0625

Max Act: 2.9357. Min Act: -0.0000

Data Index: 787692 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 4.0625. Min Range: -4.0625

Max Act: 3.0511. Min Act: -0.0000

Data Index: 986137 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 4.0625. Min Range: -4.0625

Max Act: 2.7659. Min Act: -0.0000

Data Index: 107140 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 4.0625. Min Range: -4.0625

Max Act: 2.6482. Min Act: -0.0000

Data Index: 856359 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 4.0625. Min Range: -4.0625

Max Act: 2.9389. Min Act: -0.0000

Data Index: 744049 (C4 (Web Text))

Max Activating Token Index: 407