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

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

Neuron 2730 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.2599. Min Act: -0.0001

Data Index: 392254 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.3060. Min Act: -0.0001

Data Index: 909981 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1965. Min Act: -0.0001

Data Index: 951987 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1083. Min Act: -0.0001

Data Index: 277415 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0563. Min Act: -0.0001

Data Index: 679045 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1273001 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1065. Min Act: -0.0001

Data Index: 642579 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1149549 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0587. Min Act: -0.0001

Data Index: 1319590 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1537. Min Act: -0.0001

Data Index: 34834 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0846. Min Act: -0.0001

Data Index: 962130 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1053. Min Act: -0.0001

Data Index: 253915 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1053. Min Act: -0.0001

Data Index: 4608 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1184. Min Act: -0.0001

Data Index: 554151 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.1325. Min Act: -0.0001

Data Index: 799532 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0866. Min Act: -0.0001

Data Index: 643745 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.3060. Min Range: -1.3060

Max Act: 0.9915. Min Act: -0.0001

Data Index: 1184860 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0394. Min Act: -0.0001

Data Index: 872604 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0260. Min Act: -0.0001

Data Index: 133861 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.3060. Min Range: -1.3060

Max Act: 1.0475. Min Act: -0.0001

Data Index: 515712 (C4 (Web Text))

Max Activating Token Index: 837