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

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

Neuron 3492 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: 0.2970. Min Range: -0.2970

Max Act: 0.2758. Min Act: -0.0001

Data Index: 74842 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1028397 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2685. Min Act: -0.0001

Data Index: 230937 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1354423 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1980. Min Act: -0.0000

Data Index: 329525 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1166438 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.2075. Min Act: -0.0001

Data Index: 266244 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1916. Min Act: -0.0001

Data Index: 256530 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1796. Min Act: -0.0001

Data Index: 222311 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1971. Min Act: -0.0000

Data Index: 396151 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1578. Min Act: -0.0000

Data Index: 348776 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1652. Min Act: -0.0000

Data Index: 97397 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1131403 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1417. Min Act: -0.0001

Data Index: 450450 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1695. Min Act: -0.0001

Data Index: 730134 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1569. Min Act: -0.0001

Data Index: 530821 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1247055 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1351369 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1118810 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.2970. Min Range: -0.2970

Max Act: 0.1430. Min Act: -0.0001

Data Index: 593031 (C4 (Web Text))

Max Activating Token Index: 812