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

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

Neuron 2011 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: 3.9537. Min Range: -3.9537

Max Act: 3.8025. Min Act: -0.0001

Data Index: 400638 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.9537. Min Act: -0.0001

Data Index: 261360 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.7752. Min Act: -0.0001

Data Index: 120086 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.7801. Min Act: -0.0001

Data Index: 29915 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.6875. Min Act: -0.0001

Data Index: 963368 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.5240. Min Act: -0.0001

Data Index: 155171 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.3567. Min Act: -0.0001

Data Index: 508306 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.4415. Min Act: -0.0001

Data Index: 91308 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.4146. Min Act: -0.0001

Data Index: 352959 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.4338. Min Act: -0.0001

Data Index: 592889 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.0069. Min Act: -0.0001

Data Index: 168838 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.1544. Min Act: -0.0001

Data Index: 1293653 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.1752. Min Act: -0.0001

Data Index: 1315945 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.0433. Min Act: -0.0001

Data Index: 1146707 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 3.9537. Min Range: -3.9537

Max Act: 2.9420. Min Act: -0.0001

Data Index: 633502 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 3.9537. Min Range: -3.9537

Max Act: 2.8911. Min Act: -0.0001

Data Index: 1187977 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 3.9537. Min Range: -3.9537

Max Act: 2.8318. Min Act: -0.0001

Data Index: 585386 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.9537. Min Range: -3.9537

Max Act: 2.9568. Min Act: -0.0001

Data Index: 136635 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.9537. Min Range: -3.9537

Max Act: 3.0648. Min Act: -0.0001

Data Index: 1224880 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 3.9537. Min Range: -3.9537

Max Act: 2.6509. Min Act: -0.0001

Data Index: 141836 (C4 (Web Text))

Max Activating Token Index: 436