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

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

Neuron 95 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: 0.0940. Min Range: -0.0940

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1023459 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1070767 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0000

Data Index: 213351 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1320648 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1173726 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0836. Min Act: -0.0000

Data Index: 153862 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0791. Min Act: -0.0000

Data Index: 412879 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0861. Min Act: -0.0000

Data Index: 610848 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0722. Min Act: -0.0000

Data Index: 242048 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1089103 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1063842 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0714. Min Act: -0.0000

Data Index: 188309 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0740. Min Act: -0.0000

Data Index: 560325 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1124995 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1010077 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0699. Min Act: -0.0000

Data Index: 134470 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0684. Min Act: -0.0000

Data Index: 909354 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1144530 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0650. Min Act: -0.0000

Data Index: 981567 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0630. Min Act: -0.0001

Data Index: 456902 (C4 (Web Text))

Max Activating Token Index: 441