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

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

Neuron 3613 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1703. Min Range: -1.1703

Max Act: 1.1703. Min Act: -0.0000

Data Index: 958470 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.1703. Min Range: -1.1703

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1199001 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.1703. Min Range: -1.1703

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1011830 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.1703. Min Range: -1.1703

Max Act: 1.0006. Min Act: -0.0000

Data Index: 819608 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.1703. Min Range: -1.1703

Max Act: 1.0101. Min Act: -0.0000

Data Index: 704251 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8740. Min Act: -0.0000

Data Index: 274663 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8919. Min Act: -0.0000

Data Index: 361984 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8855. Min Act: -0.0000

Data Index: 906466 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1180933 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.9329. Min Act: -0.0000

Data Index: 870688 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1341383 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.7988. Min Act: -0.0000

Data Index: 170518 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8389. Min Act: -0.0000

Data Index: 175225 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1111005 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1277524 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.6911. Min Act: -0.0000

Data Index: 609120 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.7649. Min Act: -0.0000

Data Index: 167259 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.7751. Min Act: -0.0000

Data Index: 773583 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1164585 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 1.1703. Min Range: -1.1703

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1334199 (C4 (Web Text))

Max Activating Token Index: 13