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

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

Neuron 1493 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8854. Min Act: -0.0000

Data Index: 1365436 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1617366 (Python Code)

Max Activating Token Index: 553

Text #2

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1491095 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5767. Min Act: -0.0000

Data Index: 568065 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5574. Min Act: -0.0000

Data Index: 1560136 (Python Code)

Max Activating Token Index: 25

Text #5

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5026. Min Act: -0.0000

Data Index: 1488735 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5125. Min Act: -0.0000

Data Index: 1611095 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4976. Min Act: -0.0000

Data Index: 1425852 (Python Code)

Max Activating Token Index: 893

Text #8

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4856. Min Act: -0.0000

Data Index: 1431864 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1513556 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1416650 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5304. Min Act: -0.0000

Data Index: 37559 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4889. Min Act: -0.0000

Data Index: 1511989 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4823. Min Act: -0.0000

Data Index: 1643692 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1364626 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4189. Min Act: -0.0000

Data Index: 1506555 (Python Code)

Max Activating Token Index: 288

Text #16

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1506112 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4155. Min Act: -0.0000

Data Index: 1597257 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1365432 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1581834 (Python Code)

Max Activating Token Index: 902