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

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

Neuron 1596 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: 3.1856. Min Range: -3.1856

Max Act: 3.1856. Min Act: -0.0000

Data Index: 1135300 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.7360. Min Act: -0.0000

Data Index: 1605056 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.8902. Min Act: -0.0000

Data Index: 1500273 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.6920. Min Act: -0.0000

Data Index: 517776 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.6438. Min Act: -0.0000

Data Index: 132793 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.5170. Min Act: -0.0000

Data Index: 1494888 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.6109. Min Act: -0.0000

Data Index: 384871 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.4652. Min Act: -0.0000

Data Index: 1133170 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.5681. Min Act: -0.0000

Data Index: 309962 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.5531. Min Act: -0.0000

Data Index: 706084 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.5181. Min Act: -0.0000

Data Index: 876493 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.3940. Min Act: -0.0000

Data Index: 233909 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.5292. Min Act: -0.0000

Data Index: 607906 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.2589. Min Act: -0.0000

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.5031. Min Act: -0.0000

Data Index: 374827 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.3801. Min Act: -0.0000

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.4851. Min Act: -0.0000

Data Index: 1339800 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.2138. Min Act: -0.0000

Data Index: 1607367 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.7416. Min Act: -0.0000

Data Index: 175068 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 3.1856. Min Range: -3.1856

Max Act: 2.4516. Min Act: -0.0000

Data Index: 280505 (C4 (Web Text))

Max Activating Token Index: 927