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

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

Neuron 4849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.6401. Min Act: -0.0000

Data Index: 346776 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1372441 (Python Code)

Max Activating Token Index: 309

Text #2

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1614340 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4743. Min Act: -0.0000

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4154. Min Act: -0.0000

Data Index: 798512 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1656955 (Python Code)

Max Activating Token Index: 372

Text #7

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1177289 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1206012 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1038407 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.2270. Min Act: -0.0000

Data Index: 921621 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1276098 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1437. Min Act: -0.0000

Data Index: 492138 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1520. Min Act: -0.0000

Data Index: 979302 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1900. Min Act: -0.0000

Data Index: 614113 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1638580 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1071723 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.1491. Min Act: -0.0000

Data Index: 118004 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1171819 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.0789. Min Act: -0.0000

Data Index: 953606 (C4 (Web Text))

Max Activating Token Index: 633