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

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

Neuron 2670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.6867. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.6101. Min Act: -0.0000

Data Index: 145472 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.6125. Min Act: -0.0000

Data Index: 996310 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.6359. Min Act: -0.0000

Data Index: 723656 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4969. Min Act: -0.0000

Data Index: 1194508 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4735. Min Act: -0.0000

Data Index: 598180 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4877. Min Act: -0.0000

Data Index: 535657 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4906. Min Act: -0.0000

Data Index: 565722 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4648. Min Act: -0.0000

Data Index: 1073994 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.3525. Min Act: -0.0000

Data Index: 176986 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4462. Min Act: -0.0000

Data Index: 217654 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4075. Min Act: -0.0000

Data Index: 914000 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.3868. Min Act: -0.0000

Data Index: 474398 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.3700. Min Act: -0.0000

Data Index: 240309 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.4857. Min Act: -0.0000

Data Index: 903446 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.2823. Min Act: -0.0000

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.2824. Min Act: -0.0000

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.2552. Min Act: -0.0000

Data Index: 797047 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.2344. Min Act: -0.0000

Data Index: 176092 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 2.6867. Min Range: -2.6867

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1160338 (C4 (Web Text))

Max Activating Token Index: 758