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

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

Neuron 2706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9664. Min Act: -0.0001

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9881. Min Act: -0.0001

Data Index: 240762 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8371. Min Act: -0.0001

Data Index: 475296 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7696. Min Act: -0.0001

Data Index: 596693 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7483. Min Act: -0.0001

Data Index: 856616 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7813. Min Act: -0.0001

Data Index: 336638 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7054. Min Act: -0.0001

Data Index: 986125 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6948. Min Act: -0.0001

Data Index: 127383 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6965. Min Act: -0.0001

Data Index: 494514 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7051. Min Act: -0.0001

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6700. Min Act: -0.0001

Data Index: 498543 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6635. Min Act: -0.0001

Data Index: 213701 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7028. Min Act: -0.0001

Data Index: 847219 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6107. Min Act: -0.0001

Data Index: 1199298 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1104534 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6608. Min Act: -0.0001

Data Index: 11987 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1135029 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6403. Min Act: -0.0001

Data Index: 870626 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6186. Min Act: -0.0001

Data Index: 433104 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.5333. Min Act: -0.0001

Data Index: 983158 (C4 (Web Text))

Max Activating Token Index: 656