Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3972 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5619. Min Act: -0.0000

Data Index: 185154 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5775. Min Act: -0.0000

Data Index: 203507 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5399. Min Act: -0.0000

Data Index: 754596 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5168. Min Act: -0.0001

Data Index: 374041 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1067573 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1316696 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5094. Min Act: -0.0000

Data Index: 567441 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4860. Min Act: -0.0001

Data Index: 477725 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4487. Min Act: -0.0000

Data Index: 292481 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4630. Min Act: -0.0001

Data Index: 329663 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4630. Min Act: -0.0001

Data Index: 990036 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1314270 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4762. Min Act: -0.0000

Data Index: 262124 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4372. Min Act: -0.0000

Data Index: 501070 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4694. Min Act: -0.0000

Data Index: 699537 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4330. Min Act: -0.0001

Data Index: 367880 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4448. Min Act: -0.0000

Data Index: 834787 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4404. Min Act: -0.0000

Data Index: 741186 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4270. Min Act: -0.0000

Data Index: 437493 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4312. Min Act: -0.0001

Data Index: 130842 (C4 (Web Text))

Max Activating Token Index: 712