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

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

Neuron 1854 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5577. Min Act: -0.0002

Data Index: 1537222 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5536. Min Act: -0.0002

Data Index: 1565720 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5642. Min Act: -0.0002

Data Index: 1371810 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5549. Min Act: -0.0002

Data Index: 1531745 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5488. Min Act: -0.0002

Data Index: 1585037 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5467. Min Act: -0.0002

Data Index: 1533961 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5378. Min Act: -0.0002

Data Index: 1428716 (Python Code)

Max Activating Token Index: 857

Text #7

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5546. Min Act: -0.0002

Data Index: 1609983 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5419. Min Act: -0.0002

Data Index: 1502708 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5448. Min Act: -0.0002

Data Index: 1595332 (Python Code)

Max Activating Token Index: 201

Text #10

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5416. Min Act: -0.0002

Data Index: 1622740 (Python Code)

Max Activating Token Index: 308

Text #11

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5529. Min Act: -0.0002

Data Index: 1608251 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5408. Min Act: -0.0002

Data Index: 270068 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5443. Min Act: -0.0002

Data Index: 1389341 (Python Code)

Max Activating Token Index: 203

Text #14

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5371. Min Act: -0.0002

Data Index: 1431692 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5326. Min Act: -0.0002

Data Index: 1532497 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5382. Min Act: -0.0002

Data Index: 1552180 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5352. Min Act: -0.0002

Data Index: 1410139 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5326. Min Act: -0.0002

Data Index: 1572432 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5261. Min Act: -0.0002

Data Index: 1562101 (Python Code)

Max Activating Token Index: 46