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

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

Neuron 2368 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4027. Min Range: -2.4027

Max Act: 2.4027. Min Act: -0.0000

Data Index: 945088 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 2.4027. Min Range: -2.4027

Max Act: 2.1838. Min Act: -0.0000

Data Index: 869733 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.4027. Min Range: -2.4027

Max Act: 2.2449. Min Act: -0.0000

Data Index: 268398 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 2.4027. Min Range: -2.4027

Max Act: 2.2160. Min Act: -0.0000

Data Index: 250210 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.4027. Min Range: -2.4027

Max Act: 2.1837. Min Act: -0.0000

Data Index: 957987 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.9946. Min Act: -0.0000

Data Index: 1367972 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.9990. Min Act: -0.0000

Data Index: 130146 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.8412. Min Act: -0.0000

Data Index: 476110 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.8376. Min Act: -0.0000

Data Index: 172442 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.9263. Min Act: -0.0000

Data Index: 42495 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.9263. Min Act: -0.0000

Data Index: 494910 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.9248. Min Act: -0.0000

Data Index: 934249 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.9810. Min Act: -0.0000

Data Index: 56900 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.6454. Min Act: -0.0000

Data Index: 28069 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.7429. Min Act: -0.0000

Data Index: 1134603 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.6431. Min Act: -0.0000

Data Index: 847317 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 2.4027. Min Range: -2.4027

Max Act: 2.0342. Min Act: -0.0000

Data Index: 1310942 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.7510. Min Act: -0.0000

Data Index: 479581 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.5401. Min Act: -0.0000

Data Index: 423925 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 2.4027. Min Range: -2.4027

Max Act: 1.8245. Min Act: -0.0000

Data Index: 730568 (C4 (Web Text))

Max Activating Token Index: 988