Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 768 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1760. Min Range: -1.1760

Max Act: 1.1760. Min Act: -0.0001

Data Index: 766086 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.9051. Min Act: -0.0001

Data Index: 465737 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8513. Min Act: -0.0001

Data Index: 429668 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1305627 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8468. Min Act: -0.0001

Data Index: 571897 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8596. Min Act: -0.0001

Data Index: 303072 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8574. Min Act: -0.0001

Data Index: 305394 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8622. Min Act: -0.0001

Data Index: 361723 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8356. Min Act: -0.0001

Data Index: 14704 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8303. Min Act: -0.0001

Data Index: 510114 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8356. Min Act: -0.0001

Data Index: 1168946 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7156. Min Act: -0.0001

Data Index: 1126139 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8087. Min Act: -0.0001

Data Index: 498243 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.8507. Min Act: -0.0001

Data Index: 457750 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1252986 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.6849. Min Act: -0.0001

Data Index: 392951 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7287. Min Act: -0.0001

Data Index: 723762 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7749. Min Act: -0.0001

Data Index: 35202 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7345. Min Act: -0.0001

Data Index: 883786 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.1760. Min Range: -1.1760

Max Act: 0.7601. Min Act: -0.0001

Data Index: 145681 (C4 (Web Text))

Max Activating Token Index: 853