Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1584 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0006

Data Index: 1191903 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0499. Min Act: -0.0006

Data Index: 1162991 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0492. Min Act: -0.0006

Data Index: 1007947 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0497. Min Act: -0.0006

Data Index: 882290 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0498. Min Act: -0.0006

Data Index: 850024 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0470. Min Act: -0.0006

Data Index: 1059840 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0479. Min Act: -0.0006

Data Index: 1178142 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0462. Min Act: -0.0005

Data Index: 671277 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0470. Min Act: -0.0006

Data Index: 57949 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1040807 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0422. Min Act: -0.0006

Data Index: 142081 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0440. Min Act: -0.0006

Data Index: 652793 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0457. Min Act: -0.0006

Data Index: 416578 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0456. Min Act: -0.0006

Data Index: 725808 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0454. Min Act: -0.0006

Data Index: 777788 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0443. Min Act: -0.0006

Data Index: 601143 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0443. Min Act: -0.0006

Data Index: 396869 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1346152 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0442. Min Act: -0.0006

Data Index: 1189461 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0422. Min Act: -0.0006

Data Index: 1045352 (C4 (Web Text))

Max Activating Token Index: 925