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

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

Neuron 1599 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: 2.7688. Min Range: -2.7688

Max Act: 2.7688. Min Act: -0.0000

Data Index: 172324 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.5010. Min Act: -0.0000

Data Index: 803856 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.4947. Min Act: -0.0000

Data Index: 422053 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.3587. Min Act: -0.0000

Data Index: 536700 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.4726. Min Act: -0.0000

Data Index: 129518 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.3606. Min Act: -0.0000

Data Index: 376431 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.4628. Min Act: -0.0000

Data Index: 185651 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.2780. Min Act: -0.0000

Data Index: 431514 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.2871. Min Act: -0.0000

Data Index: 1313675 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.3575. Min Act: -0.0000

Data Index: 461163 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 2.7688. Min Range: -2.7688

Max Act: 1.9161. Min Act: -0.0000

Data Index: 599366 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.0203. Min Act: -0.0000

Data Index: 684980 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 2.7688. Min Range: -2.7688

Max Act: 1.9863. Min Act: -0.0000

Data Index: 871278 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 2.7688. Min Range: -2.7688

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1214525 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.0164. Min Act: -0.0000

Data Index: 979510 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.1208. Min Act: -0.0000

Data Index: 255959 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.2208. Min Act: -0.0000

Data Index: 1093411 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.3414. Min Act: -0.0000

Data Index: 612021 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 2.7688. Min Range: -2.7688

Max Act: 1.8549. Min Act: -0.0000

Data Index: 413923 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 2.7688. Min Range: -2.7688

Max Act: 2.0290. Min Act: -0.0000

Data Index: 490905 (C4 (Web Text))

Max Activating Token Index: 14