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

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

Neuron 671 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3846. Min Act: -0.0001

Data Index: 736221 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3665. Min Act: -0.0000

Data Index: 738740 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3913. Min Act: -0.0000

Data Index: 497046 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3345. Min Act: -0.0001

Data Index: 537783 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1424815 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1082898 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3314. Min Act: -0.0000

Data Index: 709395 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3519. Min Act: -0.0001

Data Index: 1436388 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1295338 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3394. Min Act: -0.0001

Data Index: 487963 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1056577 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1609375 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3269. Min Act: -0.0001

Data Index: 692178 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3210. Min Act: -0.0001

Data Index: 880846 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3204. Min Act: -0.0001

Data Index: 1581776 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1547572 (Python Code)

Max Activating Token Index: 744

Text #16

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.2914. Min Act: -0.0001

Data Index: 531436 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3461. Min Act: -0.0001

Data Index: 699749 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3186. Min Act: -0.0001

Data Index: 391851 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.3913. Min Range: -0.3913

Max Act: 0.3088. Min Act: -0.0001

Data Index: 66648 (C4 (Web Text))

Max Activating Token Index: 990