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

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

Neuron 1200 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: 2.7641. Min Range: -2.7641

Max Act: 2.7641. Min Act: -0.0000

Data Index: 1162175 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.5390. Min Act: 0.0000

Data Index: 1340392 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.2905. Min Act: -0.0000

Data Index: 833532 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.2520. Min Act: -0.0000

Data Index: 23573 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.2546. Min Act: -0.0000

Data Index: 196488 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.2193. Min Act: 0.0000

Data Index: 664900 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.2028. Min Act: -0.0000

Data Index: 1000685 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.1276. Min Act: 0.0000

Data Index: 375144 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9698. Min Act: -0.0000

Data Index: 779164 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.0436. Min Act: -0.0000

Data Index: 483530 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9229. Min Act: -0.0000

Data Index: 279075 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9891. Min Act: 0.0000

Data Index: 185310 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9988. Min Act: -0.0000

Data Index: 351880 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9844. Min Act: -0.0000

Data Index: 222757 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 2.7641. Min Range: -2.7641

Max Act: 2.0791. Min Act: -0.0000

Data Index: 531049 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9394. Min Act: -0.0000

Data Index: 882321 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9266. Min Act: -0.0000

Data Index: 639490 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9211. Min Act: -0.0000

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.9086. Min Act: -0.0000

Data Index: 478313 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 2.7641. Min Range: -2.7641

Max Act: 1.8086. Min Act: -0.0000

Data Index: 712997 (C4 (Web Text))

Max Activating Token Index: 123