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

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

Neuron 4840 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: 1.6126. Min Range: -1.6126

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1406904 (Python Code)

Max Activating Token Index: 501

Text #1

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1619120 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.2327. Min Act: -0.0000

Data Index: 770266 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1609783 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1598743 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.2294. Min Act: -0.0000

Data Index: 754247 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1492420 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1330237 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1611036 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1047566 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1160929 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1496985 (Python Code)

Max Activating Token Index: 685

Text #12

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1344871 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.6126. Min Range: -1.6126

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1638786 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 1.6126. Min Range: -1.6126

Max Act: 0.9836. Min Act: -0.0000

Data Index: 932584 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.6126. Min Range: -1.6126

Max Act: 0.9870. Min Act: -0.0000

Data Index: 333001 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.6126. Min Range: -1.6126

Max Act: 0.9795. Min Act: -0.0000

Data Index: 424615 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.6126. Min Range: -1.6126

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1246662 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.6126. Min Range: -1.6126

Max Act: 0.9643. Min Act: -0.0000

Data Index: 757881 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 1.6126. Min Range: -1.6126

Max Act: 0.9643. Min Act: -0.0000

Data Index: 569805 (C4 (Web Text))

Max Activating Token Index: 500