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

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

Neuron 1123 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.9559. Min Act: -0.0001

Data Index: 1038576 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.9846. Min Act: -0.0001

Data Index: 945797 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8999. Min Act: -0.0000

Data Index: 20631 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8899. Min Act: -0.0001

Data Index: 692728 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8754. Min Act: -0.0001

Data Index: 967621 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.9002. Min Act: -0.0000

Data Index: 522940 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8206. Min Act: -0.0001

Data Index: 220620 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8855. Min Act: -0.0001

Data Index: 608608 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8898. Min Act: -0.0001

Data Index: 43216 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8325. Min Act: -0.0000

Data Index: 352355 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8476. Min Act: -0.0001

Data Index: 23917 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8217. Min Act: -0.0001

Data Index: 205190 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.7835. Min Act: -0.0001

Data Index: 580501 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8700. Min Act: -0.0001

Data Index: 527251 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8121. Min Act: -0.0000

Data Index: 912761 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8105. Min Act: -0.0000

Data Index: 544409 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8279. Min Act: -0.0001

Data Index: 7440 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1196315 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.7781. Min Act: -0.0000

Data Index: 693646 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.9846. Min Range: -0.9846

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1051117 (C4 (Web Text))

Max Activating Token Index: 595