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

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

Neuron 4034 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: 2.3595. Min Range: -2.3595

Max Act: 2.3595. Min Act: -0.0000

Data Index: 530764 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.7174. Min Act: -0.0000

Data Index: 517695 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.5210. Min Act: -0.0000

Data Index: 653691 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.7249. Min Act: -0.0000

Data Index: 158794 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1246151 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.5782. Min Act: -0.0000

Data Index: 245596 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.6139. Min Act: -0.0000

Data Index: 998677 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.4350. Min Act: -0.0000

Data Index: 689092 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.3680. Min Act: -0.0000

Data Index: 36434 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1276946 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.3333. Min Act: -0.0000

Data Index: 560754 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.4013. Min Act: -0.0000

Data Index: 615458 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.3356. Min Act: -0.0000

Data Index: 749886 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1066071 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.1930. Min Act: -0.0000

Data Index: 678369 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.1243. Min Act: -0.0000

Data Index: 297699 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.1353. Min Act: -0.0000

Data Index: 537367 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 2.3595. Min Range: -2.3595

Max Act: 0.9728. Min Act: -0.0000

Data Index: 443622 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 2.3595. Min Range: -2.3595

Max Act: 1.0947. Min Act: -0.0000

Data Index: 1349733 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 2.3595. Min Range: -2.3595

Max Act: 0.9870. Min Act: -0.0000

Data Index: 47904 (C4 (Web Text))

Max Activating Token Index: 117