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

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

Neuron 4658 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.7981. Min Act: -0.0000

Data Index: 531338 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6447. Min Act: -0.0000

Data Index: 122226 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5975. Min Act: -0.0000

Data Index: 764516 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1265634 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5907. Min Act: -0.0000

Data Index: 382901 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5256. Min Act: -0.0000

Data Index: 36061 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1014859 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5964. Min Act: -0.0000

Data Index: 345942 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5136. Min Act: -0.0000

Data Index: 453454 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5131. Min Act: -0.0000

Data Index: 330028 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1135091 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4868. Min Act: -0.0000

Data Index: 150369 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.5037. Min Act: -0.0000

Data Index: 945263 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4292. Min Act: -0.0000

Data Index: 659730 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1323714 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4460. Min Act: -0.0000

Data Index: 416666 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4542. Min Act: -0.0000

Data Index: 846804 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.3900. Min Act: -0.0000

Data Index: 700056 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4279. Min Act: -0.0000

Data Index: 645086 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.7981. Min Range: -0.7981

Max Act: 0.4113. Min Act: -0.0000

Data Index: 42201 (C4 (Web Text))

Max Activating Token Index: 142