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

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

Neuron 1992 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: 0.4692. Min Range: -0.4692

Max Act: 0.4629. Min Act: -0.0001

Data Index: 671105 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3455. Min Act: -0.0002

Data Index: 79290 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4692. Min Act: -0.0002

Data Index: 1070171 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1222939 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4004. Min Act: -0.0001

Data Index: 683800 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3284. Min Act: -0.0001

Data Index: 830920 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4100. Min Act: -0.0001

Data Index: 1530012 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4026. Min Act: -0.0001

Data Index: 1281829 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3291. Min Act: -0.0001

Data Index: 622941 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3581. Min Act: -0.0002

Data Index: 887975 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3454. Min Act: -0.0001

Data Index: 396743 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3531. Min Act: -0.0001

Data Index: 672312 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3548. Min Act: -0.0001

Data Index: 1548737 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3492. Min Act: -0.0002

Data Index: 934242 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3501. Min Act: -0.0002

Data Index: 640210 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3580. Min Act: -0.0002

Data Index: 536202 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3382. Min Act: -0.0001

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3700. Min Act: -0.0002

Data Index: 591367 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3469. Min Act: -0.0001

Data Index: 1578617 (Python Code)

Max Activating Token Index: 751

Text #19

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3459. Min Act: -0.0001

Data Index: 1204983 (C4 (Web Text))

Max Activating Token Index: 609