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

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

Neuron 2137 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: 3.1546. Min Range: -3.1546

Max Act: 3.1546. Min Act: -0.0000

Data Index: 392557 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.6736. Min Act: -0.0000

Data Index: 1068430 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.6123. Min Act: -0.0000

Data Index: 488241 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.5726. Min Act: -0.0000

Data Index: 241756 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.5660. Min Act: -0.0000

Data Index: 714306 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.4982. Min Act: -0.0000

Data Index: 1307239 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.4632. Min Act: -0.0000

Data Index: 861975 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.4315. Min Act: -0.0000

Data Index: 300345 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.4374. Min Act: -0.0000

Data Index: 528043 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.3654. Min Act: -0.0000

Data Index: 1002302 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.3297. Min Act: -0.0000

Data Index: 1279707 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.1797. Min Act: -0.0000

Data Index: 1157036 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.3981. Min Act: -0.0000

Data Index: 983371 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.2571. Min Act: -0.0000

Data Index: 522154 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.3802. Min Act: -0.0000

Data Index: 778168 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.1332. Min Act: -0.0000

Data Index: 337235 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.3667. Min Act: -0.0000

Data Index: 1141290 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.2071. Min Act: -0.0000

Data Index: 183934 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.2693. Min Act: -0.0000

Data Index: 568651 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 3.1546. Min Range: -3.1546

Max Act: 2.1458. Min Act: -0.0000

Data Index: 297807 (C4 (Web Text))

Max Activating Token Index: 658