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

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

Neuron 93 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4371. Min Act: -0.0003

Data Index: 645396 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4624. Min Act: -0.0003

Data Index: 1057839 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4506. Min Act: -0.0003

Data Index: 535518 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4448. Min Act: -0.0003

Data Index: 512097 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4402. Min Act: -0.0003

Data Index: 1312608 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4241. Min Act: -0.0003

Data Index: 937329 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3940. Min Act: -0.0003

Data Index: 1056607 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4018. Min Act: -0.0003

Data Index: 740496 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4095. Min Act: -0.0003

Data Index: 1325935 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4021. Min Act: -0.0003

Data Index: 65244 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4604. Min Act: -0.0003

Data Index: 619964 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3911. Min Act: -0.0003

Data Index: 728922 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3921. Min Act: -0.0003

Data Index: 1264657 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4031. Min Act: -0.0003

Data Index: 334933 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3849. Min Act: -0.0003

Data Index: 1297308 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3756. Min Act: -0.0003

Data Index: 1059731 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3702. Min Act: -0.0003

Data Index: 390083 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4083. Min Act: -0.0003

Data Index: 804559 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3486. Min Act: -0.0003

Data Index: 1290462 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4068. Min Act: -0.0003

Data Index: 16495 (C4 (Web Text))

Max Activating Token Index: 328