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

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

Neuron 3682 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: 1.2350. Min Range: -1.2350

Max Act: 1.2350. Min Act: -0.0000

Data Index: 75668 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.2207. Min Act: -0.0000

Data Index: 78382 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1186342 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.1115. Min Act: -0.0000

Data Index: 849308 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0890. Min Act: -0.0000

Data Index: 83163 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1336532 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0458. Min Act: -0.0000

Data Index: 560966 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.2350. Min Range: -1.2350

Max Act: 1.0382. Min Act: -0.0000

Data Index: 118987 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9846. Min Act: -0.0000

Data Index: 223908 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9896. Min Act: -0.0000

Data Index: 301996 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1347680 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9097. Min Act: -0.0000

Data Index: 535146 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9489. Min Act: -0.0000

Data Index: 129078 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1178783 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1348420 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1200826 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8596. Min Act: -0.0000

Data Index: 197469 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8992. Min Act: -0.0000

Data Index: 467821 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.7991. Min Act: -0.0000

Data Index: 812198 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.2350. Min Range: -1.2350

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1131223 (C4 (Web Text))

Max Activating Token Index: 176