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

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

Neuron 4035 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2883. Min Range: -4.2883

Max Act: 4.2883. Min Act: 0.0000

Data Index: 749877 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.8442. Min Act: -0.0000

Data Index: 903148 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.6920. Min Act: -0.0000

Data Index: 1185817 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.8877. Min Act: -0.0000

Data Index: 704506 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.1463. Min Act: -0.0000

Data Index: 297994 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.8324. Min Act: -0.0000

Data Index: 336167 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.4734. Min Act: 0.0000

Data Index: 384753 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.2462. Min Act: -0.0000

Data Index: 917444 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.7852. Min Act: -0.0000

Data Index: 297165 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.1961. Min Act: -0.0000

Data Index: 1019515 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.0923. Min Act: -0.0000

Data Index: 745427 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.1884. Min Act: -0.0000

Data Index: 33284 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.1582. Min Act: -0.0000

Data Index: 450052 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 4.2883. Min Range: -4.2883

Max Act: 3.1367. Min Act: -0.0000

Data Index: 561844 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.9180. Min Act: -0.0000

Data Index: 318795 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.8939. Min Act: -0.0000

Data Index: 519033 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.8835. Min Act: -0.0000

Data Index: 227031 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.9804. Min Act: -0.0000

Data Index: 513679 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.7772. Min Act: 0.0000

Data Index: 101202 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 4.2883. Min Range: -4.2883

Max Act: 2.9313. Min Act: -0.0000

Data Index: 105976 (C4 (Web Text))

Max Activating Token Index: 956