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

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

Neuron 207 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.8455. Min Act: -0.0001

Data Index: 1044704 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.6726. Min Act: -0.0000

Data Index: 931865 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.6691. Min Act: -0.0001

Data Index: 908032 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.7885. Min Act: -0.0001

Data Index: 133659 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.5594. Min Act: -0.0000

Data Index: 51684 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.5924. Min Act: -0.0000

Data Index: 845004 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.5536. Min Act: -0.0001

Data Index: 258590 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.5388. Min Act: -0.0000

Data Index: 891968 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.8231. Min Act: -0.0000

Data Index: 868769 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.5036. Min Act: -0.0001

Data Index: 751016 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1020712 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.4562. Min Act: -0.0000

Data Index: 851296 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1081465 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1331345 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.4378. Min Act: -0.0001

Data Index: 1317649 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.3746. Min Act: -0.0001

Data Index: 40101 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.2950. Min Act: -0.0000

Data Index: 884663 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.3299. Min Act: -0.0000

Data Index: 323541 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.2796. Min Act: -0.0001

Data Index: 663693 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.8455. Min Range: -1.8455

Max Act: 1.2737. Min Act: -0.0001

Data Index: 373030 (C4 (Web Text))

Max Activating Token Index: 132