Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.9219. Min Act: -0.0001

Data Index: 1527278 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1450935 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1593595 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1476541 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.8135. Min Act: -0.0001

Data Index: 1455337 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7537. Min Act: -0.0001

Data Index: 1522106 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7379. Min Act: -0.0001

Data Index: 1628140 (Python Code)

Max Activating Token Index: 724

Text #7

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1538231 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1429495 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6816. Min Act: -0.0001

Data Index: 1538622 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6545. Min Act: -0.0001

Data Index: 1532998 (Python Code)

Max Activating Token Index: 142

Text #11

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1624076 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1476581 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1610871 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6643. Min Act: -0.0001

Data Index: 1547768 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1583912 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6552. Min Act: -0.0001

Data Index: 1507752 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6116. Min Act: -0.0001

Data Index: 1432435 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1540427 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.9219. Min Range: -0.9219

Max Act: 0.6085. Min Act: -0.0001

Data Index: 1554841 (Python Code)

Max Activating Token Index: 355