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

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

Neuron 3668 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: 1.2472. Min Range: -1.2472

Max Act: 1.2472. Min Act: -0.0000

Data Index: 279194 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9510. Min Act: -0.0000

Data Index: 42005 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1163705 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1002291 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8334. Min Act: -0.0000

Data Index: 518457 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8151. Min Act: -0.0000

Data Index: 120585 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1309984 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1135365 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1119526 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7689. Min Act: -0.0000

Data Index: 224808 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7667. Min Act: -0.0000

Data Index: 411853 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7219. Min Act: -0.0000

Data Index: 331902 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.6978. Min Act: -0.0000

Data Index: 63827 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7039. Min Act: -0.0000

Data Index: 561318 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.6991. Min Act: -0.0000

Data Index: 817393 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1343188 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7107. Min Act: -0.0000

Data Index: 471544 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1307196 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7011. Min Act: -0.0000

Data Index: 870213 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.6995. Min Act: -0.0000

Data Index: 638526 (C4 (Web Text))

Max Activating Token Index: 412