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

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

Neuron 1612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4522. Min Act: -0.0001

Data Index: 168992 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4894. Min Act: -0.0001

Data Index: 646906 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5145. Min Act: -0.0001

Data Index: 144945 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4958. Min Act: -0.0001

Data Index: 580916 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4950. Min Act: -0.0001

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4852. Min Act: -0.0001

Data Index: 1004162 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4696. Min Act: -0.0001

Data Index: 231754 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1054700 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4477. Min Act: -0.0001

Data Index: 241682 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4289. Min Act: -0.0001

Data Index: 526157 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1241582 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4304. Min Act: -0.0001

Data Index: 757866 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4122. Min Act: -0.0001

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.3967. Min Act: -0.0001

Data Index: 1192664 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.3902. Min Act: -0.0001

Data Index: 1152829 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.3924. Min Act: -0.0001

Data Index: 1133547 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4100. Min Act: -0.0001

Data Index: 1099328 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.3746. Min Act: -0.0001

Data Index: 28950 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1313510 (C4 (Web Text))

Max Activating Token Index: 156