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

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

Neuron 1592 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2915. Min Act: -0.0001

Data Index: 976554 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1570496 (Python Code)

Max Activating Token Index: 511

Text #2

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2314. Min Act: -0.0001

Data Index: 812647 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1005848 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1418601 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1454893 (Python Code)

Max Activating Token Index: 553

Text #6

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2593. Min Act: -0.0001

Data Index: 1391375 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2372. Min Act: -0.0001

Data Index: 1434693 (Python Code)

Max Activating Token Index: 670

Text #8

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1644681 (Python Code)

Max Activating Token Index: 391

Text #9

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2159. Min Act: -0.0000

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2195. Min Act: -0.0000

Data Index: 645730 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1640108 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2057. Min Act: -0.0001

Data Index: 1077974 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.1947. Min Act: -0.0000

Data Index: 58880 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2256. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.1889. Min Act: -0.0000

Data Index: 801999 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1350188 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.1791. Min Act: -0.0001

Data Index: 194132 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.2915. Min Range: -0.2915

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1015280 (C4 (Web Text))

Max Activating Token Index: 273