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

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

Neuron 4309 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 17.1516. Min Range: -17.1516

Max Act: 17.1516. Min Act: -0.0002

Data Index: 141330 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 17.1516. Min Range: -17.1516

Max Act: 15.3058. Min Act: -0.0002

Data Index: 370851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 17.1516. Min Range: -17.1516

Max Act: 12.9662. Min Act: -0.0002

Data Index: 381079 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 17.1516. Min Range: -17.1516

Max Act: 8.4203. Min Act: -0.0002

Data Index: 1092078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 17.1516. Min Range: -17.1516

Max Act: 6.4994. Min Act: -0.0002

Data Index: 820327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 17.1516. Min Range: -17.1516

Max Act: 7.3020. Min Act: -0.0002

Data Index: 945059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 17.1516. Min Range: -17.1516

Max Act: 4.4731. Min Act: -0.0002

Data Index: 1247116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 17.1516. Min Range: -17.1516

Max Act: 3.3460. Min Act: -0.0002

Data Index: 1449128 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 17.1516. Min Range: -17.1516

Max Act: 2.3650. Min Act: -0.0002

Data Index: 20262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.9310. Min Act: -0.0002

Data Index: 878694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.3712. Min Act: -0.0002

Data Index: 727944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.4835. Min Act: -0.0002

Data Index: 1430332 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.3692. Min Act: -0.0002

Data Index: 1605502 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.0832. Min Act: -0.0002

Data Index: 873132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.0612. Min Act: -0.0002

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.0038. Min Act: -0.0002

Data Index: 913732 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 17.1516. Min Range: -17.1516

Max Act: 0.9883. Min Act: -0.0002

Data Index: 293405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 17.1516. Min Range: -17.1516

Max Act: 1.0070. Min Act: -0.0002

Data Index: 16344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 17.1516. Min Range: -17.1516

Max Act: 0.9350. Min Act: -0.0002

Data Index: 128735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 17.1516. Min Range: -17.1516

Max Act: 0.8728. Min Act: -0.0002

Data Index: 477463 (C4 (Web Text))

Max Activating Token Index: 1023