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

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

Neuron 2664 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.4535. Min Act: -0.0000

Data Index: 1027732 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1202536 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.2958. Min Act: -0.0000

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.4089. Min Act: -0.0000

Data Index: 486621 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1233448 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.1399. Min Act: -0.0000

Data Index: 106808 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.1145. Min Act: -0.0000

Data Index: 573471 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1076773 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.0370. Min Act: -0.0000

Data Index: 881252 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.9751. Min Act: -0.0000

Data Index: 914705 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.4535. Min Range: -1.4535

Max Act: 1.0712. Min Act: -0.0000

Data Index: 402515 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1144179 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.9096. Min Act: -0.0000

Data Index: 194677 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.9952. Min Act: -0.0000

Data Index: 390881 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1150062 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1250938 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1317606 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1297845 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1175109 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 1.4535. Min Range: -1.4535

Max Act: 0.8363. Min Act: -0.0000

Data Index: 254845 (C4 (Web Text))

Max Activating Token Index: 836