Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1285 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.3066. Min Act: -0.0000

Data Index: 822153 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1517912 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1072795 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0823. Min Act: -0.0000

Data Index: 125747 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1039953 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0075. Min Act: -0.0000

Data Index: 538053 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1295389 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0748. Min Act: -0.0000

Data Index: 936438 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0980. Min Act: -0.0000

Data Index: 361172 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0351. Min Act: -0.0000

Data Index: 663905 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1032277 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0906. Min Act: -0.0000

Data Index: 931672 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1381541 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0165. Min Act: -0.0000

Data Index: 784156 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0689. Min Act: -0.0000

Data Index: 685139 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0294. Min Act: -0.0000

Data Index: 160924 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0278. Min Act: -0.0000

Data Index: 985199 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1517188 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 1.3066. Min Range: -1.3066

Max Act: 0.9906. Min Act: -0.0000

Data Index: 900230 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 1.3066. Min Range: -1.3066

Max Act: 1.0016. Min Act: -0.0000

Data Index: 224941 (C4 (Web Text))

Max Activating Token Index: 778