Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 349 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.7106. Min Act: -0.0002

Data Index: 389538 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5784. Min Act: -0.0002

Data Index: 186501 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6492. Min Act: -0.0002

Data Index: 142127 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5983. Min Act: -0.0002

Data Index: 303188 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5927. Min Act: -0.0002

Data Index: 120594 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5038. Min Act: -0.0002

Data Index: 859325 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5856. Min Act: -0.0002

Data Index: 276324 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.6431. Min Act: -0.0002

Data Index: 350312 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5692. Min Act: -0.0002

Data Index: 764157 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5459. Min Act: -0.0002

Data Index: 575211 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5799. Min Act: -0.0002

Data Index: 785582 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5756. Min Act: -0.0002

Data Index: 1218364 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5851. Min Act: -0.0002

Data Index: 674230 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5118. Min Act: -0.0002

Data Index: 371111 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5605. Min Act: -0.0002

Data Index: 713959 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5163. Min Act: -0.0002

Data Index: 523232 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5287. Min Act: -0.0002

Data Index: 339642 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.4920. Min Act: -0.0002

Data Index: 101918 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.4780. Min Act: -0.0002

Data Index: 1117922 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.7106. Min Range: -0.7106

Max Act: 0.5609. Min Act: -0.0002

Data Index: 765682 (C4 (Web Text))

Max Activating Token Index: 280