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

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

Neuron 4143 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.1858. Min Act: -0.0000

Data Index: 1215110 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.0590. Min Act: -0.0000

Data Index: 812574 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.3247. Min Act: -0.0000

Data Index: 1235556 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.1738. Min Act: -0.0000

Data Index: 1337059 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.0835. Min Act: -0.0000

Data Index: 1193485 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.3689. Min Act: -0.0000

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 3.3689. Min Range: -3.3689

Max Act: 3.1599. Min Act: -0.0000

Data Index: 142977 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9719. Min Act: -0.0000

Data Index: 285213 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9734. Min Act: -0.0000

Data Index: 818378 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.8312. Min Act: -0.0000

Data Index: 497464 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9662. Min Act: -0.0000

Data Index: 855084 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9622. Min Act: -0.0000

Data Index: 354266 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9734. Min Act: -0.0000

Data Index: 1338149 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9711. Min Act: -0.0000

Data Index: 749436 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9491. Min Act: -0.0000

Data Index: 1078462 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9449. Min Act: -0.0000

Data Index: 737691 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.7922. Min Act: -0.0000

Data Index: 804766 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.9260. Min Act: -0.0000

Data Index: 563271 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.8974. Min Act: -0.0000

Data Index: 736734 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 3.3689. Min Range: -3.3689

Max Act: 2.8969. Min Act: -0.0000

Data Index: 38451 (C4 (Web Text))

Max Activating Token Index: 270