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

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

Neuron 83 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4587. Min Act: -0.0000

Data Index: 370040 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4281. Min Act: -0.0001

Data Index: 192883 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1341603 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3418. Min Act: -0.0001

Data Index: 635454 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3278. Min Act: -0.0000

Data Index: 227851 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1180655 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3156. Min Act: -0.0000

Data Index: 760642 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1340423 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3126. Min Act: -0.0001

Data Index: 639550 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.3043. Min Act: -0.0001

Data Index: 595267 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2982. Min Act: -0.0000

Data Index: 565017 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2919. Min Act: -0.0000

Data Index: 987180 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2923. Min Act: -0.0000

Data Index: 134148 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2900. Min Act: -0.0000

Data Index: 108818 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2742. Min Act: -0.0000

Data Index: 801127 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2741. Min Act: -0.0001

Data Index: 414098 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2899. Min Act: -0.0000

Data Index: 815436 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1189854 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2609. Min Act: -0.0000

Data Index: 809388 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.4587. Min Range: -0.4587

Max Act: 0.2663. Min Act: -0.0001

Data Index: 300336 (C4 (Web Text))

Max Activating Token Index: 255