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

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

Neuron 3926 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.5217. Min Act: -0.0001

Data Index: 1028301 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.2920. Min Act: -0.0001

Data Index: 1586 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1339957 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.2224. Min Act: -0.0001

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1228195 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.0883. Min Act: -0.0001

Data Index: 656649 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.0756. Min Act: -0.0001

Data Index: 97852 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.0100. Min Act: -0.0001

Data Index: 799488 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9873. Min Act: -0.0001

Data Index: 830672 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9070. Min Act: -0.0001

Data Index: 103373 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 1.5217. Min Range: -1.5217

Max Act: 1.0873. Min Act: -0.0001

Data Index: 375159 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9738. Min Act: -0.0000

Data Index: 509077 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9281. Min Act: -0.0001

Data Index: 572721 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9521. Min Act: -0.0001

Data Index: 1202287 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1341524 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1215636 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9303. Min Act: -0.0001

Data Index: 1194705 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.8591. Min Act: -0.0000

Data Index: 653690 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.9406. Min Act: -0.0001

Data Index: 165179 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.5217. Min Range: -1.5217

Max Act: 0.8464. Min Act: -0.0000

Data Index: 547843 (C4 (Web Text))

Max Activating Token Index: 236