Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0958. Min Range: -1.0958

Max Act: 1.0958. Min Act: -0.0000

Data Index: 414070 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 1.0958. Min Range: -1.0958

Max Act: 1.0362. Min Act: -0.0000

Data Index: 369048 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.0958. Min Range: -1.0958

Max Act: 1.0037. Min Act: -0.0000

Data Index: 354838 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.9648. Min Act: -0.0000

Data Index: 75277 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8923. Min Act: -0.0000

Data Index: 897308 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.9192. Min Act: -0.0000

Data Index: 388409 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.9439. Min Act: -0.0000

Data Index: 992325 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.9166. Min Act: -0.0000

Data Index: 525987 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8923. Min Act: -0.0000

Data Index: 556463 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1133764 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8496. Min Act: -0.0000

Data Index: 469735 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1122251 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8668. Min Act: -0.0000

Data Index: 172312 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8394. Min Act: -0.0000

Data Index: 468453 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8257. Min Act: -0.0000

Data Index: 25614 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8326. Min Act: -0.0000

Data Index: 19644 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8318. Min Act: -0.0000

Data Index: 60060 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8269. Min Act: -0.0000

Data Index: 487116 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7920. Min Act: -0.0000

Data Index: 283949 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7679. Min Act: -0.0000

Data Index: 486954 (C4 (Web Text))

Max Activating Token Index: 593