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

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

Neuron 5005 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7024. Min Range: -2.7024

Max Act: 2.7024. Min Act: -0.0000

Data Index: 1087483 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 2.7024. Min Range: -2.7024

Max Act: 2.0666. Min Act: -0.0000

Data Index: 1127962 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 2.7024. Min Range: -2.7024

Max Act: 2.0464. Min Act: -0.0000

Data Index: 710428 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.9234. Min Act: -0.0000

Data Index: 320300 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.8470. Min Act: -0.0000

Data Index: 445422 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.8427. Min Act: -0.0000

Data Index: 1055784 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1326341 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.7720. Min Act: -0.0000

Data Index: 659950 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.7658. Min Act: -0.0000

Data Index: 1069784 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.7900. Min Act: -0.0000

Data Index: 348560 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.6284. Min Act: -0.0000

Data Index: 1149183 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.4781. Min Act: -0.0000

Data Index: 379593 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.4412. Min Act: -0.0000

Data Index: 264008 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.5185. Min Act: -0.0000

Data Index: 8742 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.4911. Min Act: -0.0000

Data Index: 366513 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.3695. Min Act: -0.0000

Data Index: 387076 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1109887 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.4457. Min Act: -0.0000

Data Index: 754887 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1237103 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 2.7024. Min Range: -2.7024

Max Act: 1.3287. Min Act: -0.0000

Data Index: 190492 (C4 (Web Text))

Max Activating Token Index: 654