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

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

Neuron 2063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1368. Min Range: -2.1368

Max Act: 2.1368. Min Act: -0.0000

Data Index: 1391938 (Python Code)

Max Activating Token Index: 557

Text #1

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9756. Min Act: -0.0000

Data Index: 1591484 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1546754 (Python Code)

Max Activating Token Index: 793

Text #3

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.7529. Min Act: -0.0000

Data Index: 1484561 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.7713. Min Act: -0.0000

Data Index: 1579965 (Python Code)

Max Activating Token Index: 752

Text #5

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1517349 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1613448 (Python Code)

Max Activating Token Index: 857

Text #7

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.6481. Min Act: -0.0000

Data Index: 1033147 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1561351 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.5927. Min Act: -0.0000

Data Index: 1096618 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.6288. Min Act: -0.0000

Data Index: 567974 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.4875. Min Act: -0.0000

Data Index: 4636 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1320272 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.5931. Min Act: -0.0000

Data Index: 957784 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.4775. Min Act: -0.0000

Data Index: 446318 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.4855. Min Act: -0.0000

Data Index: 375029 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1360556 (Python Code)

Max Activating Token Index: 936

Text #17

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1505114 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.4215. Min Act: -0.0000

Data Index: 497365 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1096817 (C4 (Web Text))

Max Activating Token Index: 847