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

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

Neuron 5139 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4472. Min Range: -6.4472

Max Act: 6.4472. Min Act: -0.0000

Data Index: 391541 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 6.4472. Min Range: -6.4472

Max Act: 5.6737. Min Act: -0.0000

Data Index: 587339 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 6.4472. Min Range: -6.4472

Max Act: 5.8083. Min Act: -0.0000

Data Index: 789292 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 6.4472. Min Range: -6.4472

Max Act: 5.4702. Min Act: -0.0000

Data Index: 537248 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.3192. Min Act: -0.0000

Data Index: 994512 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 6.4472. Min Range: -6.4472

Max Act: 5.0550. Min Act: -0.0000

Data Index: 276936 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.7123. Min Act: -0.0000

Data Index: 131329 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.5395. Min Act: -0.0000

Data Index: 283654 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.6837. Min Act: -0.0000

Data Index: 1302531 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.5727. Min Act: -0.0000

Data Index: 826477 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.4292. Min Act: -0.0000

Data Index: 185516 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.2759. Min Act: -0.0000

Data Index: 36508 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.8749. Min Act: -0.0000

Data Index: 523469 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 6.4472. Min Range: -6.4472

Max Act: 4.1055. Min Act: -0.0000

Data Index: 936917 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.8039. Min Act: -0.0000

Data Index: 1315394 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.7791. Min Act: -0.0000

Data Index: 25178 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.2978. Min Act: -0.0000

Data Index: 1238513 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.1313. Min Act: -0.0000

Data Index: 814754 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.2722. Min Act: -0.0000

Data Index: 294722 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 6.4472. Min Range: -6.4472

Max Act: 3.3683. Min Act: -0.0000

Data Index: 1125130 (C4 (Web Text))

Max Activating Token Index: 670