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

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

Neuron 2003 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9758. Min Range: -2.9758

Max Act: 2.9758. Min Act: -0.0000

Data Index: 10852 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.9758. Min Range: -2.9758

Max Act: 1.5621. Min Act: -0.0000

Data Index: 391165 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 2.9758. Min Range: -2.9758

Max Act: 1.2350. Min Act: -0.0000

Data Index: 622616 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.9758. Min Range: -2.9758

Max Act: 1.2081. Min Act: -0.0000

Data Index: 207766 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1153879 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 2.9758. Min Range: -2.9758

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1251671 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 2.9758. Min Range: -2.9758

Max Act: 1.0506. Min Act: -0.0000

Data Index: 849597 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8875. Min Act: -0.0000

Data Index: 846264 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.9273. Min Act: -0.0000

Data Index: 989553 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8789. Min Act: -0.0000

Data Index: 667601 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 2.9758. Min Range: -2.9758

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1329009 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.7804. Min Act: -0.0000

Data Index: 392366 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8015. Min Act: -0.0000

Data Index: 32957 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.9295. Min Act: -0.0000

Data Index: 983921 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1002563 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8352. Min Act: -0.0000

Data Index: 944134 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8873. Min Act: -0.0000

Data Index: 260650 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.8800. Min Act: -0.0000

Data Index: 306203 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.9059. Min Act: -0.0000

Data Index: 486475 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.9758. Min Range: -2.9758

Max Act: 0.6153. Min Act: -0.0000

Data Index: 798792 (C4 (Web Text))

Max Activating Token Index: 722