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

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

Neuron 1492 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1505602 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1527030 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1370128 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1621907 (Python Code)

Max Activating Token Index: 359

Text #4

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1520663 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1365059 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1640252 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1541311 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1629641 (Python Code)

Max Activating Token Index: 633

Text #9

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1369605 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1593730 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1371338 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1387844 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1529700 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1533420 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1426058 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1509192 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1393915 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1371368 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1505607 (Python Code)

Max Activating Token Index: 725