Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3747 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1807. Min Act: -0.0001

Data Index: 673783 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0659. Min Act: -0.0001

Data Index: 191979 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1224. Min Act: -0.0001

Data Index: 1298245 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0471. Min Act: -0.0001

Data Index: 1085108 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1218. Min Act: -0.0001

Data Index: 918566 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1157. Min Act: -0.0001

Data Index: 679706 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0819. Min Act: -0.0001

Data Index: 869416 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0458. Min Act: -0.0001

Data Index: 1479885 (Python Code)

Max Activating Token Index: 867

Text #8

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0241. Min Act: -0.0001

Data Index: 1269282 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0405. Min Act: -0.0001

Data Index: 302649 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0426. Min Act: -0.0001

Data Index: 134509 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9787. Min Act: -0.0001

Data Index: 1171739 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0302. Min Act: -0.0001

Data Index: 125874 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0023. Min Act: -0.0001

Data Index: 176047 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0017. Min Act: -0.0001

Data Index: 802577 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0308. Min Act: -0.0001

Data Index: 1498696 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0268. Min Act: -0.0001

Data Index: 954157 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9418. Min Act: -0.0001

Data Index: 1301276 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1076680 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.0404. Min Act: -0.0001

Data Index: 915136 (C4 (Web Text))

Max Activating Token Index: 715