Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1888 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6027. Min Act: -0.0004

Data Index: 1512814 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5646. Min Act: -0.0004

Data Index: 1423998 (Python Code)

Max Activating Token Index: 819

Text #2

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7000. Min Act: -0.0004

Data Index: 1384740 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7008. Min Act: -0.0004

Data Index: 1585710 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7314. Min Act: -0.0004

Data Index: 1411561 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5983. Min Act: -0.0004

Data Index: 1589964 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6578. Min Act: -0.0004

Data Index: 1392542 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4991. Min Act: -0.0004

Data Index: 1509625 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6470. Min Act: -0.0004

Data Index: 1364982 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5963. Min Act: -0.0004

Data Index: 1629911 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6126. Min Act: -0.0004

Data Index: 1508697 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4707. Min Act: -0.0004

Data Index: 1487572 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5533. Min Act: -0.0004

Data Index: 1549714 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6653. Min Act: -0.0004

Data Index: 1371122 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5122. Min Act: -0.0004

Data Index: 1610107 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5087. Min Act: -0.0004

Data Index: 1513767 (Python Code)

Max Activating Token Index: 922

Text #16

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6158. Min Act: -0.0004

Data Index: 1493883 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6269. Min Act: -0.0004

Data Index: 1412178 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5315. Min Act: -0.0004

Data Index: 1641900 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5841. Min Act: -0.0004

Data Index: 1577464 (Python Code)

Max Activating Token Index: 361