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

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

Neuron 2241 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: 0.8944. Min Range: -0.8944

Max Act: 0.8944. Min Act: -0.0001

Data Index: 311149 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.8697. Min Act: -0.0001

Data Index: 906904 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.8202. Min Act: -0.0001

Data Index: 1302256 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.7914. Min Act: -0.0001

Data Index: 971278 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.7113. Min Act: -0.0001

Data Index: 267001 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.7449. Min Act: -0.0001

Data Index: 632979 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6390. Min Act: -0.0001

Data Index: 621692 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6239. Min Act: -0.0001

Data Index: 1027003 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6154. Min Act: -0.0001

Data Index: 699975 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6392. Min Act: -0.0001

Data Index: 260113 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6076. Min Act: -0.0001

Data Index: 670902 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6333. Min Act: -0.0001

Data Index: 97461 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6107. Min Act: -0.0001

Data Index: 201186 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5745. Min Act: -0.0001

Data Index: 522415 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6151. Min Act: -0.0001

Data Index: 842095 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6006. Min Act: -0.0001

Data Index: 84188 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5586. Min Act: -0.0001

Data Index: 86970 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5706. Min Act: -0.0001

Data Index: 921734 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5768. Min Act: -0.0001

Data Index: 389836 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5669. Min Act: -0.0001

Data Index: 729877 (C4 (Web Text))

Max Activating Token Index: 431