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

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

Neuron 632 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: 0.6958. Min Range: -0.6958

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1543009 (Python Code)

Max Activating Token Index: 733

Text #1

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1550803 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1471229 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1406871 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1422471 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1516085 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1570969 (Python Code)

Max Activating Token Index: 286

Text #7

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1465696 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1411297 (Python Code)

Max Activating Token Index: 135

Text #9

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1616626 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1435510 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1506348 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1409071 (Python Code)

Max Activating Token Index: 459

Text #13

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1381896 (Python Code)

Max Activating Token Index: 554

Text #14

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1490024 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1559132 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1488452 (Python Code)

Max Activating Token Index: 442

Text #17

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1370698 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1612530 (Python Code)

Max Activating Token Index: 330

Text #19

Max Range: 0.6958. Min Range: -0.6958

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1612712 (Python Code)

Max Activating Token Index: 733