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

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

Neuron 28 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: 0.6926. Min Range: -0.6926

Max Act: 0.6810. Min Act: -0.0001

Data Index: 1129107 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6276. Min Act: -0.0001

Data Index: 515832 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6926. Min Act: -0.0001

Data Index: 151298 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1145754 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6505. Min Act: -0.0000

Data Index: 958401 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6461. Min Act: -0.0001

Data Index: 842288 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6471. Min Act: -0.0000

Data Index: 485512 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6491. Min Act: -0.0001

Data Index: 833200 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6212. Min Act: -0.0001

Data Index: 228572 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1316208 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.6018. Min Act: -0.0001

Data Index: 603614 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5803. Min Act: -0.0000

Data Index: 129619 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5585. Min Act: -0.0000

Data Index: 659017 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5624. Min Act: -0.0001

Data Index: 949209 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5029. Min Act: -0.0001

Data Index: 839006 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5321. Min Act: -0.0000

Data Index: 848780 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5147. Min Act: -0.0001

Data Index: 738341 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.5229. Min Act: -0.0000

Data Index: 310326 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.4987. Min Act: -0.0001

Data Index: 888673 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.6926. Min Range: -0.6926

Max Act: 0.4777. Min Act: -0.0000

Data Index: 728873 (C4 (Web Text))

Max Activating Token Index: 383