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

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

Neuron 6055 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: 3.2979. Min Range: -3.2979

Max Act: 3.2979. Min Act: -0.0000

Data Index: 788949 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1255. Min Act: -0.0000

Data Index: 1063874 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.9233. Min Act: -0.0000

Data Index: 979317 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.0382. Min Act: -0.0000

Data Index: 748714 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1160. Min Act: -0.0000

Data Index: 16137 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.0454. Min Act: -0.0000

Data Index: 417626 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.1834. Min Act: -0.0001

Data Index: 73550 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.8922. Min Act: -0.0000

Data Index: 1082757 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.0209. Min Act: -0.0000

Data Index: 1258316 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.0689. Min Act: -0.0000

Data Index: 1215872 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.7382. Min Act: -0.0000

Data Index: 838822 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.9348. Min Act: -0.0000

Data Index: 846980 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.5306. Min Act: -0.0000

Data Index: 859783 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1133835 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.5151. Min Act: -0.0000

Data Index: 1231808 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.8660. Min Act: -0.0000

Data Index: 876280 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.4899. Min Act: -0.0000

Data Index: 1304727 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.8757. Min Act: -0.0000

Data Index: 892142 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.4896. Min Act: -0.0001

Data Index: 1341642 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 3.2979. Min Range: -3.2979

Max Act: 2.3053. Min Act: -0.0001

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 798