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

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

Neuron 5333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1445801 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1511526 (Python Code)

Max Activating Token Index: 865

Text #2

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1376402 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1613862 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1448571 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1639768 (Python Code)

Max Activating Token Index: 663

Text #6

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1472654 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1525975 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1466351 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1504315 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1600614 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1654749 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1476973 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1416052 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1471506 (Python Code)

Max Activating Token Index: 961

Text #15

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1480228 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1523937 (Python Code)

Max Activating Token Index: 470

Text #17

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1497369 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1638227 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 0.7053. Min Range: -0.7053

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1549938 (Python Code)

Max Activating Token Index: 47