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

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

Neuron 2958 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1550737 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.1002. Min Act: -0.0000

Data Index: 1636706 (Python Code)

Max Activating Token Index: 657

Text #2

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.2847. Min Act: -0.0000

Data Index: 1424422 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.2631. Min Act: -0.0000

Data Index: 1273931 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0052. Min Act: -0.0000

Data Index: 1471413 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.2068. Min Act: -0.0000

Data Index: 1400247 (Python Code)

Max Activating Token Index: 788

Text #6

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0920. Min Act: -0.0000

Data Index: 1621203 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9422. Min Act: -0.0000

Data Index: 1570943 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.8355. Min Act: -0.0000

Data Index: 1446489 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0432. Min Act: -0.0000

Data Index: 1215711 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9105. Min Act: -0.0000

Data Index: 1403704 (Python Code)

Max Activating Token Index: 596

Text #11

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9869. Min Act: -0.0000

Data Index: 1631195 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.1801. Min Act: -0.0000

Data Index: 1653488 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0597. Min Act: -0.0000

Data Index: 1583728 (Python Code)

Max Activating Token Index: 958

Text #14

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9329. Min Act: -0.0000

Data Index: 1599605 (Python Code)

Max Activating Token Index: 623

Text #15

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1640944 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.8733. Min Act: -0.0000

Data Index: 1384104 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9627. Min Act: -0.0000

Data Index: 1586259 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.7756. Min Act: -0.0000

Data Index: 876991 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1613964 (Python Code)

Max Activating Token Index: 43