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

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

Neuron 723 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.8904. Min Act: -0.0000

Data Index: 595565 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.8340. Min Act: -0.0000

Data Index: 699824 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1259911 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1025358 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7249. Min Act: -0.0000

Data Index: 126959 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1535188 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1270337 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1365682 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7026. Min Act: -0.0000

Data Index: 405912 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7416. Min Act: -0.0000

Data Index: 682563 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6933. Min Act: -0.0000

Data Index: 788359 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1298456 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1587696 (Python Code)

Max Activating Token Index: 129

Text #13

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6606. Min Act: -0.0000

Data Index: 723803 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7000. Min Act: -0.0000

Data Index: 693245 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6697. Min Act: -0.0000

Data Index: 734002 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6523. Min Act: -0.0000

Data Index: 227820 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6238. Min Act: -0.0000

Data Index: 748751 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.7018. Min Act: -0.0000

Data Index: 786769 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.8904. Min Range: -0.8904

Max Act: 0.6447. Min Act: -0.0000

Data Index: 562921 (C4 (Web Text))

Max Activating Token Index: 516