Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3940 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.4999. Min Act: -0.0000

Data Index: 749436 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.3092. Min Act: -0.0000

Data Index: 954873 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1526161 (Python Code)

Max Activating Token Index: 697

Text #3

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1406719 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.9642. Min Act: -0.0000

Data Index: 944949 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1651669 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.8552. Min Act: -0.0000

Data Index: 195886 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.8072. Min Act: -0.0000

Data Index: 217091 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1404724 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1474395 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1415953 (Python Code)

Max Activating Token Index: 883

Text #11

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1514906 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.8171. Min Act: -0.0000

Data Index: 441559 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1277664 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1613302 (Python Code)

Max Activating Token Index: 341

Text #15

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1444591 (Python Code)

Max Activating Token Index: 229

Text #16

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1450729 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1586580 (Python Code)

Max Activating Token Index: 558

Text #18

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7818. Min Act: -0.0000

Data Index: 481025 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1458095 (Python Code)

Max Activating Token Index: 722