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

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

Neuron 2989 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: 2.3027. Min Range: -2.3027

Max Act: 2.3027. Min Act: -0.0000

Data Index: 198218 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2642. Min Act: -0.0000

Data Index: 700503 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2826. Min Act: -0.0000

Data Index: 438117 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.2774. Min Act: -0.0000

Data Index: 171978 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.9741. Min Act: -0.0000

Data Index: 712469 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.0610. Min Act: -0.0000

Data Index: 460804 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.9579. Min Act: -0.0000

Data Index: 1358746 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.9961. Min Act: -0.0000

Data Index: 187579 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.8271. Min Act: -0.0000

Data Index: 1190756 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.9314. Min Act: -0.0000

Data Index: 317525 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 2.3027. Min Range: -2.3027

Max Act: 2.0282. Min Act: -0.0000

Data Index: 850398 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1294764 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.8325. Min Act: -0.0000

Data Index: 627297 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1149169 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.6256. Min Act: -0.0000

Data Index: 910915 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.6986. Min Act: -0.0000

Data Index: 1084622 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1324052 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1338931 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.7609. Min Act: -0.0000

Data Index: 887517 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 2.3027. Min Range: -2.3027

Max Act: 1.7414. Min Act: -0.0000

Data Index: 321124 (C4 (Web Text))

Max Activating Token Index: 757