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

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

Neuron 2150 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: 0.3937. Min Range: -0.3937

Max Act: 0.3937. Min Act: -0.0001

Data Index: 298020 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.3901. Min Act: -0.0001

Data Index: 85056 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1474557 (Python Code)

Max Activating Token Index: 110

Text #3

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1092014 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2822. Min Act: -0.0001

Data Index: 458391 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2763. Min Act: -0.0001

Data Index: 85744 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2782. Min Act: -0.0001

Data Index: 446107 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1082923 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2563. Min Act: -0.0001

Data Index: 584095 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2648. Min Act: -0.0001

Data Index: 355469 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1356530 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2641. Min Act: -0.0001

Data Index: 426295 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2583. Min Act: -0.0001

Data Index: 105617 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2438. Min Act: -0.0001

Data Index: 291433 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2416. Min Act: -0.0001

Data Index: 383347 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2400. Min Act: -0.0001

Data Index: 365979 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1339728 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2374. Min Act: -0.0001

Data Index: 570104 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1277887 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.3937. Min Range: -0.3937

Max Act: 0.2425. Min Act: -0.0001

Data Index: 1043323 (C4 (Web Text))

Max Activating Token Index: 411