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

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

Neuron 1904 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1512053 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1485753 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1568732 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4114. Min Act: -0.0000

Data Index: 131084 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.4031. Min Act: -0.0000

Data Index: 409027 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1100001 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1654841 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3684. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1439280 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3845. Min Act: -0.0000

Data Index: 430033 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1400649 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3819. Min Act: -0.0000

Data Index: 417182 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1582726 (Python Code)

Max Activating Token Index: 180

Text #13

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1549638 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3545. Min Act: -0.0000

Data Index: 877687 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1401391 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3376. Min Act: -0.0000

Data Index: 912297 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1595193 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 0.4632. Min Range: -0.4632

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1541297 (Python Code)

Max Activating Token Index: 615