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

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

Neuron 6025 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.9015. Min Act: -0.0000

Data Index: 1216152 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1445880 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.1600. Min Act: -0.0000

Data Index: 900332 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1475900 (Python Code)

Max Activating Token Index: 186

Text #4

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.1479. Min Act: 0.0000

Data Index: 834715 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1604661 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1137588 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.0332. Min Act: -0.0000

Data Index: 711440 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.0415. Min Act: -0.0000

Data Index: 139720 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1630819 (Python Code)

Max Activating Token Index: 127

Text #10

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.0059. Min Act: -0.0000

Data Index: 445251 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9873. Min Act: -0.0000

Data Index: 822867 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.9015. Min Range: -1.9015

Max Act: 1.0730. Min Act: -0.0000

Data Index: 813943 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9805. Min Act: -0.0000

Data Index: 809323 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1546923 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1426739 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9302. Min Act: -0.0000

Data Index: 299207 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9105. Min Act: -0.0000

Data Index: 504824 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9138. Min Act: -0.0000

Data Index: 971953 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.9015. Min Range: -1.9015

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1440679 (Python Code)

Max Activating Token Index: 537