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

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

Neuron 2578 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.9822. Min Act: -0.0000

Data Index: 129815 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.8253. Min Act: -0.0000

Data Index: 826959 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.7795. Min Act: -0.0000

Data Index: 1040478 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 2.1241. Min Range: -2.1241

Max Act: 2.1241. Min Act: -0.0000

Data Index: 1188825 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.8422. Min Act: -0.0000

Data Index: 653464 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1321883 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.8491. Min Act: -0.0000

Data Index: 640947 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.8316. Min Act: -0.0000

Data Index: 615885 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.7889. Min Act: -0.0000

Data Index: 122916 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.5088. Min Act: -0.0000

Data Index: 609555 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.4898. Min Act: -0.0000

Data Index: 1248407 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.5114. Min Act: -0.0000

Data Index: 118753 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1245788 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.4400. Min Act: -0.0000

Data Index: 78086 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.2863. Min Act: -0.0000

Data Index: 306403 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.2736. Min Act: -0.0000

Data Index: 248696 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.4296. Min Act: -0.0000

Data Index: 373781 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.3963. Min Act: -0.0000

Data Index: 804371 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.3212. Min Act: -0.0000

Data Index: 529112 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 2.1241. Min Range: -2.1241

Max Act: 1.2929. Min Act: -0.0000

Data Index: 527309 (C4 (Web Text))

Max Activating Token Index: 340