Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.7927. Min Act: -0.0000

Data Index: 270112 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.7939. Min Act: -0.0000

Data Index: 210776 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.4808. Min Act: -0.0000

Data Index: 823372 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.6318. Min Act: -0.0000

Data Index: 149063 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.6730. Min Act: -0.0000

Data Index: 230163 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.6657. Min Act: -0.0000

Data Index: 860719 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5733. Min Act: -0.0000

Data Index: 714850 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.6201. Min Act: -0.0000

Data Index: 158067 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5732. Min Act: -0.0000

Data Index: 898375 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5848. Min Act: -0.0000

Data Index: 663090 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1138624 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5941. Min Act: -0.0000

Data Index: 611888 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5721. Min Act: -0.0000

Data Index: 567467 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1268672 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1257490 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.6090. Min Act: -0.0000

Data Index: 94849 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1238629 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5570. Min Act: -0.0000

Data Index: 197258 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5183. Min Act: -0.0000

Data Index: 712181 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.7939. Min Range: -0.7939

Max Act: 0.5214. Min Act: -0.0000

Data Index: 336442 (C4 (Web Text))

Max Activating Token Index: 693