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

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

Neuron 4043 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.5265. Min Act: -0.0001

Data Index: 729190 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.6665. Min Act: -0.0001

Data Index: 669601 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.3217. Min Act: -0.0001

Data Index: 1061461 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.2900. Min Act: -0.0001

Data Index: 745813 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.9984. Min Act: -0.0001

Data Index: 373959 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.6665. Min Range: -1.6665

Max Act: 1.1031. Min Act: -0.0001

Data Index: 209231 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.9198. Min Act: -0.0001

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.9130. Min Act: -0.0001

Data Index: 366079 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.9548. Min Act: -0.0001

Data Index: 1298375 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.9175. Min Act: -0.0001

Data Index: 998183 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8872. Min Act: -0.0001

Data Index: 696720 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.9697. Min Act: -0.0001

Data Index: 778808 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8642. Min Act: -0.0001

Data Index: 675021 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8902. Min Act: -0.0001

Data Index: 711781 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8628. Min Act: -0.0001

Data Index: 131140 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8258. Min Act: -0.0001

Data Index: 62105 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1063521 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1157992 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.7859. Min Act: -0.0001

Data Index: 477471 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.6665. Min Range: -1.6665

Max Act: 0.7909. Min Act: -0.0001

Data Index: 59272 (C4 (Web Text))

Max Activating Token Index: 972