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

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

Neuron 4705 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: 1.1068. Min Range: -1.1068

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1389690 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.0885. Min Act: -0.0000

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.0451. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.0575. Min Act: -0.0000

Data Index: 776306 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1468666 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1299726 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1041008 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1605595 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9806. Min Act: -0.0000

Data Index: 13924 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1535294 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1591837 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1364727 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8999. Min Act: -0.0000

Data Index: 352132 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1479525 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1234181 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1621994 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1595888 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1490986 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1600024 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8877. Min Act: -0.0000

Data Index: 409973 (C4 (Web Text))

Max Activating Token Index: 68