Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.5374. Min Act: -0.0001

Data Index: 517774 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.5206. Min Act: -0.0001

Data Index: 788476 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.5102. Min Act: -0.0001

Data Index: 463629 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4192. Min Act: -0.0001

Data Index: 1275939 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1349302 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3991. Min Act: -0.0001

Data Index: 861190 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4334. Min Act: -0.0001

Data Index: 280324 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4492. Min Act: -0.0001

Data Index: 297060 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4042. Min Act: -0.0001

Data Index: 764046 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1323432 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1130118 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3534. Min Act: -0.0001

Data Index: 407974 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3723. Min Act: -0.0001

Data Index: 200423 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3815. Min Act: -0.0001

Data Index: 677331 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3569. Min Act: -0.0001

Data Index: 85148 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3746. Min Act: -0.0001

Data Index: 854465 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3482. Min Act: -0.0001

Data Index: 345214 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3596. Min Act: -0.0001

Data Index: 798530 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3533. Min Act: -0.0001

Data Index: 821960 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3786. Min Act: -0.0001

Data Index: 1049321 (C4 (Web Text))

Max Activating Token Index: 194