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

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

Neuron 5389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.9806. Min Act: -0.0000

Data Index: 682160 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.8354. Min Act: -0.0000

Data Index: 692655 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.9096. Min Act: -0.0000

Data Index: 799127 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.7289. Min Act: -0.0000

Data Index: 1225534 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.9972. Min Act: -0.0000

Data Index: 255488 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.8307. Min Act: -0.0000

Data Index: 1046112 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.6380. Min Act: -0.0000

Data Index: 247361 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.7480. Min Act: -0.0000

Data Index: 185115 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.6004. Min Act: -0.0000

Data Index: 777917 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.7392. Min Act: -0.0000

Data Index: 1221341 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.5462. Min Act: -0.0000

Data Index: 448944 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.5268. Min Act: -0.0000

Data Index: 71104 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.3708. Min Act: -0.0000

Data Index: 89214 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.4644. Min Act: -0.0000

Data Index: 119504 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.5874. Min Act: -0.0000

Data Index: 1288064 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.5571. Min Act: -0.0000

Data Index: 135989 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.4407. Min Act: -0.0000

Data Index: 314371 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.4376. Min Act: -0.0000

Data Index: 1083280 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.3098. Min Act: -0.0000

Data Index: 192334 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 2.9972. Min Range: -2.9972

Max Act: 2.4062. Min Act: -0.0000

Data Index: 1185305 (C4 (Web Text))

Max Activating Token Index: 729