Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2582 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0264. Min Act: -0.0001

Data Index: 78038 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9987. Min Act: -0.0001

Data Index: 96594 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9900. Min Act: -0.0001

Data Index: 618082 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0256. Min Act: -0.0001

Data Index: 68014 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0740. Min Act: -0.0001

Data Index: 180986 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9930. Min Act: -0.0001

Data Index: 794333 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0093. Min Act: -0.0001

Data Index: 1251017 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9771. Min Act: -0.0001

Data Index: 1522688 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0251. Min Act: -0.0001

Data Index: 172450 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9776. Min Act: -0.0001

Data Index: 188182 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9857. Min Act: -0.0001

Data Index: 575121 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9258. Min Act: -0.0001

Data Index: 427430 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9258. Min Act: -0.0001

Data Index: 838982 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9634. Min Act: -0.0001

Data Index: 686511 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9374. Min Act: -0.0001

Data Index: 232586 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9149. Min Act: -0.0001

Data Index: 918400 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8930. Min Act: -0.0001

Data Index: 876823 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9223. Min Act: -0.0001

Data Index: 741494 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9697. Min Act: -0.0001

Data Index: 346191 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8712. Min Act: -0.0001

Data Index: 753412 (C4 (Web Text))

Max Activating Token Index: 800