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

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

Neuron 5964 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6027. Min Range: -3.6027

Max Act: 3.6027. Min Act: -0.0000

Data Index: 587932 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.6027. Min Range: -3.6027

Max Act: 3.2512. Min Act: -0.0000

Data Index: 1282681 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.9335. Min Act: -0.0000

Data Index: 165709 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.7414. Min Act: -0.0000

Data Index: 574852 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.7034. Min Act: -0.0000

Data Index: 198230 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.6883. Min Act: -0.0000

Data Index: 1140693 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.6747. Min Act: 0.0001

Data Index: 1040606 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.7117. Min Act: -0.0000

Data Index: 648930 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.6455. Min Act: -0.0000

Data Index: 339245 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.5434. Min Act: -0.0000

Data Index: 842894 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.4187. Min Act: 0.0000

Data Index: 227387 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.3932. Min Act: -0.0000

Data Index: 447115 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.4587. Min Act: -0.0000

Data Index: 1217348 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.5978. Min Act: -0.0000

Data Index: 672907 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.5517. Min Act: -0.0000

Data Index: 1294896 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.2555. Min Act: -0.0000

Data Index: 411480 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.3704. Min Act: -0.0000

Data Index: 77518 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.4040. Min Act: -0.0000

Data Index: 456786 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.3846. Min Act: -0.0000

Data Index: 581703 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 3.6027. Min Range: -3.6027

Max Act: 2.4898. Min Act: -0.0000

Data Index: 1310805 (C4 (Web Text))

Max Activating Token Index: 455