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

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

Neuron 4633 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0087. Min Range: -6.0087

Max Act: 5.5070. Min Act: -0.0001

Data Index: 324029 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 6.0087. Min Range: -6.0087

Max Act: 6.0087. Min Act: -0.0000

Data Index: 870913 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 6.0087. Min Range: -6.0087

Max Act: 5.6303. Min Act: -0.0001

Data Index: 975091 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.9252. Min Act: -0.0001

Data Index: 73347 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 6.0087. Min Range: -6.0087

Max Act: 5.1114. Min Act: -0.0000

Data Index: 1167460 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.6202. Min Act: -0.0000

Data Index: 1341992 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.5064. Min Act: -0.0001

Data Index: 542951 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.7000. Min Act: -0.0001

Data Index: 516148 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.5762. Min Act: -0.0000

Data Index: 325943 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.0848. Min Act: -0.0001

Data Index: 328259 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.2004. Min Act: -0.0001

Data Index: 371358 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.0230. Min Act: -0.0001

Data Index: 798583 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.6933. Min Act: -0.0001

Data Index: 132870 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.8578. Min Act: -0.0000

Data Index: 913563 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.7803. Min Act: -0.0000

Data Index: 304532 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.8900. Min Act: -0.0001

Data Index: 498321 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.5824. Min Act: -0.0001

Data Index: 241063 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 6.0087. Min Range: -6.0087

Max Act: 4.1949. Min Act: -0.0000

Data Index: 447932 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.6504. Min Act: -0.0000

Data Index: 34361 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 6.0087. Min Range: -6.0087

Max Act: 3.4819. Min Act: -0.0000

Data Index: 130243 (C4 (Web Text))

Max Activating Token Index: 988