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

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

Neuron 1593 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9565. Min Range: -2.9565

Max Act: 2.9565. Min Act: -0.0000

Data Index: 1428621 (Python Code)

Max Activating Token Index: 970

Text #1

Max Range: 2.9565. Min Range: -2.9565

Max Act: 2.4286. Min Act: -0.0000

Data Index: 1656716 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 2.9565. Min Range: -2.9565

Max Act: 2.1820. Min Act: 0.0000

Data Index: 1471470 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 2.9565. Min Range: -2.9565

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1424834 (Python Code)

Max Activating Token Index: 409

Text #4

Max Range: 2.9565. Min Range: -2.9565

Max Act: 2.0191. Min Act: -0.0000

Data Index: 1613704 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.9009. Min Act: -0.0000

Data Index: 1209611 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.7720. Min Act: -0.0000

Data Index: 765212 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.9762. Min Act: -0.0000

Data Index: 1453068 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.8006. Min Act: -0.0000

Data Index: 1546979 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.7802. Min Act: 0.0000

Data Index: 1370596 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.6660. Min Act: -0.0000

Data Index: 876861 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.7449. Min Act: -0.0000

Data Index: 993028 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1474499 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.6653. Min Act: -0.0000

Data Index: 555337 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.5789. Min Act: -0.0000

Data Index: 770698 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1390905 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.4775. Min Act: -0.0000

Data Index: 49709 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.4517. Min Act: -0.0000

Data Index: 566114 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1574682 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 2.9565. Min Range: -2.9565

Max Act: 1.6159. Min Act: 0.0000

Data Index: 355669 (C4 (Web Text))

Max Activating Token Index: 408