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

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

Neuron 5103 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: 0.1512. Min Range: -0.1512

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1307072 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1498. Min Act: -0.0001

Data Index: 444390 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1427. Min Act: -0.0000

Data Index: 252724 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0001

Data Index: 709289 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1446785 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1476789 (Python Code)

Max Activating Token Index: 638

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1360874 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1242496 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1038. Min Act: -0.0000

Data Index: 253088 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1267759 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1550573 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1523436 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1037. Min Act: -0.0001

Data Index: 440769 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1274232 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1179529 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1033. Min Act: -0.0000

Data Index: 490124 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0956. Min Act: -0.0000

Data Index: 673875 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0982. Min Act: -0.0001

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0942. Min Act: -0.0001

Data Index: 496933 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0860. Min Act: -0.0000

Data Index: 690424 (C4 (Web Text))

Max Activating Token Index: 398