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

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

Neuron 2468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.4922. Min Act: -0.0000

Data Index: 285262 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1349733 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1087507 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1272547 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.0191. Min Act: -0.0000

Data Index: 678369 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1443048 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1055379 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8469. Min Act: -0.0000

Data Index: 98167 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1438910 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8766. Min Act: -0.0000

Data Index: 798201 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9508. Min Act: -0.0000

Data Index: 689092 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8860. Min Act: -0.0000

Data Index: 36434 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.9125. Min Act: -0.0000

Data Index: 75871 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8490. Min Act: -0.0000

Data Index: 8437 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8318. Min Act: -0.0000

Data Index: 382116 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8252. Min Act: -0.0000

Data Index: 239795 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8246. Min Act: -0.0000

Data Index: 715298 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7934. Min Act: -0.0000

Data Index: 212582 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.7893. Min Act: -0.0000

Data Index: 691161 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.4922. Min Range: -1.4922

Max Act: 0.8103. Min Act: -0.0000

Data Index: 290130 (C4 (Web Text))

Max Activating Token Index: 421