Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1222 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4518. Min Act: -0.0001

Data Index: 763952 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4561. Min Act: -0.0001

Data Index: 1030181 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4420. Min Act: -0.0001

Data Index: 84942 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.4045. Min Act: -0.0001

Data Index: 272073 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3895. Min Act: -0.0001

Data Index: 360031 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3860. Min Act: -0.0001

Data Index: 935920 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3860. Min Act: -0.0001

Data Index: 624414 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1295627 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1243282 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3827. Min Act: -0.0001

Data Index: 1342880 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3798. Min Act: -0.0001

Data Index: 824459 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3934. Min Act: -0.0001

Data Index: 805684 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3736. Min Act: -0.0001

Data Index: 626114 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3839. Min Act: -0.0001

Data Index: 153113 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1332604 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3791. Min Act: -0.0001

Data Index: 727430 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3603. Min Act: -0.0001

Data Index: 387186 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3572. Min Act: -0.0001

Data Index: 225290 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1060189 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1010276 (C4 (Web Text))

Max Activating Token Index: 113