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

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

Neuron 1897 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1385949 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1448356 (Python Code)

Max Activating Token Index: 348

Text #2

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1458925 (Python Code)

Max Activating Token Index: 539

Text #3

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6523. Min Act: -0.0001

Data Index: 1388111 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1374793 (Python Code)

Max Activating Token Index: 890

Text #5

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6619. Min Act: -0.0001

Data Index: 1510067 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1627135 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1537305 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1458420 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1465082 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1550215 (Python Code)

Max Activating Token Index: 83

Text #11

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1412766 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1436243 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1395392 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5530. Min Act: -0.0001

Data Index: 1436877 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1389292 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5640. Min Act: -0.0001

Data Index: 1553372 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1556874 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1362493 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 0.8052. Min Range: -0.8052

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1444940 (Python Code)

Max Activating Token Index: 681