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

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

Neuron 5289 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: 0.6736. Min Range: -0.6736

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1268602 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.6736. Min Act: -0.0000

Data Index: 58897 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1051961 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1229387 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5669. Min Act: -0.0000

Data Index: 76601 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5577. Min Act: -0.0000

Data Index: 221060 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5521. Min Act: 0.0000

Data Index: 685891 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5451. Min Act: 0.0000

Data Index: 1076257 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5172. Min Act: 0.0000

Data Index: 1042942 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5345. Min Act: -0.0000

Data Index: 676788 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1000112 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5127. Min Act: -0.0000

Data Index: 782127 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4933. Min Act: -0.0000

Data Index: 690952 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4862. Min Act: -0.0000

Data Index: 30242 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4865. Min Act: -0.0000

Data Index: 118169 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1005678 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4942. Min Act: -0.0000

Data Index: 185463 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4923. Min Act: -0.0000

Data Index: 57684 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4763. Min Act: -0.0000

Data Index: 476018 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4994. Min Act: -0.0000

Data Index: 12254 (C4 (Web Text))

Max Activating Token Index: 249