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

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

Neuron 2527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3417. Min Range: -1.3417

Max Act: 1.3417. Min Act: -0.0002

Data Index: 50640 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8433. Min Act: -0.0002

Data Index: 814130 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.9327. Min Act: -0.0001

Data Index: 162774 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.9053. Min Act: -0.0001

Data Index: 809365 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8986. Min Act: -0.0002

Data Index: 279701 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8589. Min Act: -0.0001

Data Index: 33101 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.9142. Min Act: -0.0001

Data Index: 989591 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8683. Min Act: -0.0002

Data Index: 639285 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8742. Min Act: -0.0002

Data Index: 1230381 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8079. Min Act: -0.0002

Data Index: 431577 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8508. Min Act: -0.0002

Data Index: 1021275 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.9537. Min Act: -0.0002

Data Index: 762454 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.7929. Min Act: -0.0002

Data Index: 902666 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8508. Min Act: -0.0001

Data Index: 460037 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.7540. Min Act: -0.0002

Data Index: 417587 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8215. Min Act: -0.0001

Data Index: 1328627 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8367. Min Act: -0.0002

Data Index: 871447 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8086. Min Act: -0.0001

Data Index: 394216 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.7859. Min Act: -0.0002

Data Index: 1313984 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.7992. Min Act: -0.0002

Data Index: 1138270 (C4 (Web Text))

Max Activating Token Index: 956