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

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

Neuron 2246 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: 7.4589. Min Range: -7.4589

Max Act: 7.4589. Min Act: -0.0000

Data Index: 345884 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 7.4589. Min Range: -7.4589

Max Act: 6.5033. Min Act: -0.0000

Data Index: 209419 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.1431. Min Act: -0.0000

Data Index: 69723 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.3724. Min Act: -0.0000

Data Index: 698902 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.6278. Min Act: -0.0000

Data Index: 1217774 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.3493. Min Act: -0.0000

Data Index: 1359677 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.3019. Min Act: -0.0000

Data Index: 559203 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.3145. Min Act: -0.0000

Data Index: 594432 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.4835. Min Act: -0.0000

Data Index: 298387 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.4646. Min Act: -0.0000

Data Index: 1190944 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.2617. Min Act: -0.0000

Data Index: 399349 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.3938. Min Act: -0.0000

Data Index: 814573 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.1600. Min Act: -0.0000

Data Index: 258912 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.0159. Min Act: -0.0000

Data Index: 444227 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 7.4589. Min Range: -7.4589

Max Act: 4.7734. Min Act: -0.0000

Data Index: 534331 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.0997. Min Act: -0.0000

Data Index: 450315 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 7.4589. Min Range: -7.4589

Max Act: 4.7126. Min Act: -0.0000

Data Index: 589 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.2996. Min Act: -0.0000

Data Index: 1121568 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.2515. Min Act: -0.0000

Data Index: 1152857 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 7.4589. Min Range: -7.4589

Max Act: 5.0468. Min Act: -0.0000

Data Index: 1089483 (C4 (Web Text))

Max Activating Token Index: 111