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

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

Neuron 4219 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.1565. Min Range: -9.1565

Max Act: 9.1565. Min Act: -0.0000

Data Index: 736214 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 9.1565. Min Range: -9.1565

Max Act: 8.6396. Min Act: -0.0000

Data Index: 1249837 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 9.1565. Min Range: -9.1565

Max Act: 7.5986. Min Act: -0.0000

Data Index: 181904 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 9.1565. Min Range: -9.1565

Max Act: 7.8705. Min Act: -0.0000

Data Index: 1035329 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 9.1565. Min Range: -9.1565

Max Act: 7.9237. Min Act: -0.0000

Data Index: 1058794 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 9.1565. Min Range: -9.1565

Max Act: 7.2754. Min Act: -0.0000

Data Index: 321086 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 9.1565. Min Range: -9.1565

Max Act: 7.0893. Min Act: -0.0000

Data Index: 388002 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 9.1565. Min Range: -9.1565

Max Act: 6.6702. Min Act: -0.0000

Data Index: 293734 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 9.1565. Min Range: -9.1565

Max Act: 6.6320. Min Act: -0.0000

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.9990. Min Act: -0.0000

Data Index: 1229384 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 9.1565. Min Range: -9.1565

Max Act: 6.3668. Min Act: -0.0000

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.9534. Min Act: -0.0000

Data Index: 793334 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 9.1565. Min Range: -9.1565

Max Act: 6.1312. Min Act: -0.0000

Data Index: 693404 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 9.1565. Min Range: -9.1565

Max Act: 6.1247. Min Act: -0.0000

Data Index: 1270448 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.8091. Min Act: -0.0000

Data Index: 1169557 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.8786. Min Act: -0.0000

Data Index: 608759 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.8943. Min Act: -0.0000

Data Index: 3307 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.8523. Min Act: -0.0000

Data Index: 241013 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 9.1565. Min Range: -9.1565

Max Act: 6.0350. Min Act: -0.0000

Data Index: 180416 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 9.1565. Min Range: -9.1565

Max Act: 5.5721. Min Act: -0.0000

Data Index: 1148002 (C4 (Web Text))

Max Activating Token Index: 806