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

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

Neuron 4642 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 893756 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4608. Min Act: -0.0000

Data Index: 960403 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.4520. Min Act: -0.0000

Data Index: 731274 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1176281 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3684. Min Act: -0.0000

Data Index: 339215 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1184757 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3526. Min Act: -0.0000

Data Index: 396642 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3360. Min Act: -0.0000

Data Index: 130813 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3101. Min Act: -0.0001

Data Index: 326664 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3153. Min Act: -0.0000

Data Index: 980295 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3058. Min Act: -0.0000

Data Index: 490978 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1287864 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3007. Min Act: -0.0000

Data Index: 363826 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2877. Min Act: -0.0000

Data Index: 637340 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2950. Min Act: -0.0000

Data Index: 311528 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2912. Min Act: -0.0000

Data Index: 773297 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1309757 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2852. Min Act: -0.0000

Data Index: 692459 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2744. Min Act: 0.0000

Data Index: 310547 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.2683. Min Act: -0.0000

Data Index: 569141 (C4 (Web Text))

Max Activating Token Index: 560