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

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

Neuron 4025 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.5452. Min Act: -0.0000

Data Index: 724281 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.3923. Min Act: -0.0000

Data Index: 560421 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.2588. Min Act: -0.0000

Data Index: 1256507 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.3932. Min Act: -0.0000

Data Index: 89842 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.2083. Min Act: -0.0000

Data Index: 1395609 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.3360. Min Act: -0.0000

Data Index: 47630 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.2343. Min Act: -0.0000

Data Index: 299238 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.2795. Min Act: -0.0000

Data Index: 716355 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.1860. Min Act: -0.0000

Data Index: 690874 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1220076 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.9474. Min Act: -0.0000

Data Index: 35240 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 3.5452. Min Range: -3.5452

Max Act: 3.0792. Min Act: -0.0000

Data Index: 257866 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.9081. Min Act: -0.0000

Data Index: 390897 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.6391. Min Act: -0.0000

Data Index: 269796 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.8235. Min Act: -0.0000

Data Index: 209771 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.9441. Min Act: -0.0000

Data Index: 1006579 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.8070. Min Act: -0.0000

Data Index: 568490 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.7834. Min Act: -0.0000

Data Index: 300926 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.7610. Min Act: -0.0000

Data Index: 714004 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 3.5452. Min Range: -3.5452

Max Act: 2.7469. Min Act: -0.0000

Data Index: 385733 (C4 (Web Text))

Max Activating Token Index: 467