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

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

Neuron 3130 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: 1.5134. Min Range: -1.5134

Max Act: 1.4562. Min Act: -0.0000

Data Index: 1528157 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1410999 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1371394 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1618463 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1368108 (Python Code)

Max Activating Token Index: 116

Text #5

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1565539 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1531222 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1553858 (Python Code)

Max Activating Token Index: 564

Text #8

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1379661 (Python Code)

Max Activating Token Index: 654

Text #9

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1652201 (Python Code)

Max Activating Token Index: 267

Text #10

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1443776 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1589192 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1533976 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1454004 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1503634 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1504456 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1571483 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1637305 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1540702 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 1.5134. Min Range: -1.5134

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1517061 (Python Code)

Max Activating Token Index: 701