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

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

Neuron 5055 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.8287. Min Act: -0.0000

Data Index: 904073 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7201. Min Act: -0.0000

Data Index: 378481 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6928. Min Act: -0.0000

Data Index: 982949 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6413. Min Act: -0.0000

Data Index: 147557 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6281. Min Act: -0.0000

Data Index: 325018 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5838. Min Act: -0.0000

Data Index: 52822 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5685. Min Act: -0.0000

Data Index: 319009 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5972. Min Act: -0.0000

Data Index: 962040 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5407. Min Act: -0.0000

Data Index: 548005 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6105. Min Act: -0.0000

Data Index: 524927 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5657. Min Act: -0.0000

Data Index: 435873 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1234537 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5497. Min Act: -0.0000

Data Index: 664001 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1033303 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5025. Min Act: -0.0000

Data Index: 812553 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5333. Min Act: -0.0000

Data Index: 256098 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5250. Min Act: -0.0000

Data Index: 733733 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1347585 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5060. Min Act: -0.0000

Data Index: 113471 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1263561 (C4 (Web Text))

Max Activating Token Index: 458