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

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

Neuron 1671 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7138. Min Range: -2.7138

Max Act: 2.7138. Min Act: -0.0000

Data Index: 1473290 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.9552. Min Act: -0.0000

Data Index: 1586128 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7723. Min Act: -0.0000

Data Index: 1428577 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 2.7138. Min Range: -2.7138

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1531031 (Python Code)

Max Activating Token Index: 774

Text #4

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.9353. Min Act: -0.0000

Data Index: 1404514 (Python Code)

Max Activating Token Index: 882

Text #5

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1368332 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.8535. Min Act: -0.0000

Data Index: 1570216 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.8232. Min Act: -0.0000

Data Index: 1437998 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1383618 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7908. Min Act: -0.0000

Data Index: 1621741 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1611797 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7501. Min Act: -0.0000

Data Index: 1512620 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1403079 (Python Code)

Max Activating Token Index: 460

Text #13

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7202. Min Act: -0.0000

Data Index: 1464964 (Python Code)

Max Activating Token Index: 579

Text #14

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7101. Min Act: -0.0000

Data Index: 1573780 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1576283 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1544375 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.7905. Min Act: -0.0000

Data Index: 1529201 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1528566 (Python Code)

Max Activating Token Index: 747

Text #19

Max Range: 2.7138. Min Range: -2.7138

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1468780 (Python Code)

Max Activating Token Index: 132