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

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

Neuron 255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.7317. Min Act: -0.0000

Data Index: 396540 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.7921. Min Act: -0.0000

Data Index: 201517 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.6114. Min Act: -0.0000

Data Index: 1342538 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.4855. Min Act: -0.0000

Data Index: 279489 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.4526. Min Act: -0.0000

Data Index: 19347 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.3367. Min Act: -0.0000

Data Index: 339662 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.3494. Min Act: -0.0000

Data Index: 845970 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.4803. Min Act: -0.0000

Data Index: 91200 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.1710. Min Act: -0.0000

Data Index: 1106861 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.2655. Min Act: -0.0001

Data Index: 1072694 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.2885. Min Act: -0.0000

Data Index: 979093 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.2596. Min Act: -0.0000

Data Index: 1033870 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1058136 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.2705. Min Act: -0.0000

Data Index: 1338306 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.0471. Min Act: -0.0000

Data Index: 1128982 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.0777. Min Act: -0.0000

Data Index: 271801 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.2125. Min Act: -0.0000

Data Index: 719639 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 2.7921. Min Range: -2.7921

Max Act: 2.0845. Min Act: -0.0000

Data Index: 901073 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 2.7921. Min Range: -2.7921

Max Act: 1.9704. Min Act: -0.0000

Data Index: 611690 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 2.7921. Min Range: -2.7921

Max Act: 1.9070. Min Act: -0.0000

Data Index: 190073 (C4 (Web Text))

Max Activating Token Index: 899