Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3203 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4313. Min Act: -0.0000

Data Index: 502864 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1169555 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3605. Min Act: -0.0000

Data Index: 3915 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3331. Min Act: -0.0000

Data Index: 511400 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3256. Min Act: -0.0000

Data Index: 967270 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3250. Min Act: -0.0001

Data Index: 533518 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3357. Min Act: -0.0001

Data Index: 740931 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1076601 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1152819 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1285060 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1147107 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1126277 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2865. Min Act: -0.0000

Data Index: 19739 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2951. Min Act: -0.0000

Data Index: 961306 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2734. Min Act: -0.0001

Data Index: 704363 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1311277 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2812. Min Act: -0.0000

Data Index: 117500 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2479. Min Act: -0.0000

Data Index: 112282 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1326655 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.2516. Min Act: -0.0001

Data Index: 54438 (C4 (Web Text))

Max Activating Token Index: 491