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

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

Neuron 5563 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0169. Min Range: -1.0169

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1144567 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.9946. Min Act: -0.0000

Data Index: 910089 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1528033 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1096500 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7175. Min Act: -0.0000

Data Index: 407242 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8092. Min Act: 0.0000

Data Index: 254817 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1654843 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7780. Min Act: -0.0000

Data Index: 349718 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7825. Min Act: -0.0000

Data Index: 923475 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1291005 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1194959 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7496. Min Act: -0.0000

Data Index: 440963 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7295. Min Act: -0.0000

Data Index: 165844 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1143398 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6555. Min Act: -0.0000

Data Index: 166430 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7382. Min Act: -0.0000

Data Index: 914879 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7881. Min Act: -0.0000

Data Index: 878010 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6797. Min Act: -0.0000

Data Index: 399204 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1043702 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.0169. Min Range: -1.0169

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1436367 (Python Code)

Max Activating Token Index: 490