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

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

Neuron 3002 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0001

Data Index: 57317 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0720. Min Act: -0.0001

Data Index: 516483 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1055036 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0601. Min Act: -0.0000

Data Index: 223441 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0630. Min Act: -0.0000

Data Index: 708000 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0600. Min Act: -0.0000

Data Index: 145255 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1157838 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0549. Min Act: -0.0001

Data Index: 951313 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0524. Min Act: -0.0000

Data Index: 273743 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0518. Min Act: -0.0001

Data Index: 957303 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1053595 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0550. Min Act: -0.0000

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1263161 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1238372 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0526. Min Act: -0.0000

Data Index: 609702 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1359460 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0545. Min Act: -0.0000

Data Index: 911363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1251073 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0535. Min Act: -0.0000

Data Index: 46715 (C4 (Web Text))

Max Activating Token Index: 900