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

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

Neuron 1888 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: 2.1656. Min Range: -2.1656

Max Act: 2.1656. Min Act: -0.0000

Data Index: 1576651 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.8168. Min Act: -0.0000

Data Index: 1610981 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.7457. Min Act: -0.0000

Data Index: 933717 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1590909 (Python Code)

Max Activating Token Index: 641

Text #4

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.7238. Min Act: -0.0000

Data Index: 1456916 (Python Code)

Max Activating Token Index: 538

Text #5

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.5176. Min Act: -0.0000

Data Index: 1359950 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.5259. Min Act: -0.0000

Data Index: 1488052 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1636102 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1652542 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1513434 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1486212 (Python Code)

Max Activating Token Index: 990

Text #11

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1631718 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1574016 (Python Code)

Max Activating Token Index: 579

Text #13

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1565166 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1502035 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1558198 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1444680 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3523. Min Act: -0.0000

Data Index: 740884 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1418881 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 2.1656. Min Range: -2.1656

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1610658 (Python Code)

Max Activating Token Index: 389