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

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

Neuron 1330 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.7596. Min Act: -0.0000

Data Index: 933175 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.6978. Min Act: -0.0000

Data Index: 964604 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.6408. Min Act: -0.0000

Data Index: 980291 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5531. Min Act: -0.0000

Data Index: 631478 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5526. Min Act: -0.0000

Data Index: 942935 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5862. Min Act: -0.0000

Data Index: 92146 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1062075 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5492. Min Act: -0.0000

Data Index: 266846 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1116175 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5559. Min Act: -0.0000

Data Index: 629697 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1117572 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5158. Min Act: -0.0000

Data Index: 620529 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4962. Min Act: -0.0000

Data Index: 183954 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4973. Min Act: -0.0000

Data Index: 610381 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.5137. Min Act: -0.0000

Data Index: 818739 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1325735 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4948. Min Act: -0.0000

Data Index: 461401 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4779. Min Act: -0.0000

Data Index: 273769 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4771. Min Act: -0.0000

Data Index: 186191 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.7596. Min Range: -0.7596

Max Act: 0.4752. Min Act: -0.0000

Data Index: 123882 (C4 (Web Text))

Max Activating Token Index: 562