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

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

Neuron 2605 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.6685. Min Range: -10.6685

Max Act: 10.6685. Min Act: -0.0000

Data Index: 544303 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 10.6685. Min Range: -10.6685

Max Act: 10.1397. Min Act: -0.0000

Data Index: 1093018 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 10.6685. Min Range: -10.6685

Max Act: 10.1496. Min Act: -0.0000

Data Index: 280648 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.7063. Min Act: -0.0000

Data Index: 296796 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.5523. Min Act: -0.0000

Data Index: 336912 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.5952. Min Act: -0.0000

Data Index: 275431 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.5715. Min Act: -0.0000

Data Index: 636267 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.5497. Min Act: -0.0000

Data Index: 101732 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.2918. Min Act: -0.0000

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.4291. Min Act: -0.0000

Data Index: 1321182 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.3991. Min Act: -0.0000

Data Index: 558361 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.2252. Min Act: -0.0000

Data Index: 14911 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.1897. Min Act: -0.0000

Data Index: 570045 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.2904. Min Act: -0.0000

Data Index: 1293844 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.1036. Min Act: -0.0000

Data Index: 799536 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 10.6685. Min Range: -10.6685

Max Act: 8.9785. Min Act: -0.0000

Data Index: 791628 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.1571. Min Act: -0.0000

Data Index: 135819 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.1153. Min Act: -0.0000

Data Index: 565103 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 10.6685. Min Range: -10.6685

Max Act: 8.9827. Min Act: -0.0000

Data Index: 940962 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 10.6685. Min Range: -10.6685

Max Act: 9.1089. Min Act: -0.0000

Data Index: 1176634 (C4 (Web Text))

Max Activating Token Index: 105