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

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

Neuron 3147 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: 0.5097. Min Range: -0.5097

Max Act: 0.5097. Min Act: -0.0000

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4992. Min Act: -0.0000

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4734. Min Act: -0.0000

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4688. Min Act: -0.0001

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1295621 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4751. Min Act: -0.0000

Data Index: 757595 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4724. Min Act: -0.0000

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4816. Min Act: -0.0000

Data Index: 140596 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4472. Min Act: -0.0000

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4476. Min Act: -0.0000

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1274694 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1217434 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1013785 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4050. Min Act: -0.0000

Data Index: 33833 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1647623 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4256. Min Act: -0.0000

Data Index: 212505 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4106. Min Act: -0.0000

Data Index: 807601 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4113. Min Act: -0.0000

Data Index: 103257 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3809. Min Act: -0.0000

Data Index: 170868 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1551965 (Python Code)

Max Activating Token Index: 606