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

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

Neuron 4705 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: 1.6800. Min Range: -1.6800

Max Act: 1.6336. Min Act: -0.0000

Data Index: 836822 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.6800. Min Act: -0.0000

Data Index: 745570 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.5539. Min Act: -0.0000

Data Index: 645656 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.4677. Min Act: -0.0000

Data Index: 1331019 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1341692 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.4445. Min Act: -0.0000

Data Index: 667234 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2479. Min Act: -0.0000

Data Index: 98104 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2989. Min Act: -0.0000

Data Index: 268886 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2927. Min Act: -0.0000

Data Index: 527145 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.3661. Min Act: -0.0000

Data Index: 628476 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1178046 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2681. Min Act: -0.0000

Data Index: 475689 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2669. Min Act: -0.0000

Data Index: 49382 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2533. Min Act: -0.0000

Data Index: 874714 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1039368 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1259096 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1001. Min Act: -0.0000

Data Index: 108679 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2438. Min Act: -0.0000

Data Index: 430518 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0781. Min Act: -0.0000

Data Index: 913996 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2186. Min Act: -0.0000

Data Index: 375263 (C4 (Web Text))

Max Activating Token Index: 1010