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

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

Neuron 2821 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: 0.3613. Min Range: -0.3613

Max Act: 0.3613. Min Act: -0.0000

Data Index: 283759 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3488. Min Act: -0.0000

Data Index: 478271 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3387. Min Act: -0.0000

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1000595 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3057. Min Act: -0.0001

Data Index: 813953 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3142. Min Act: -0.0000

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.3114. Min Act: -0.0000

Data Index: 89031 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1037701 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2866. Min Act: -0.0000

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2583. Min Act: -0.0000

Data Index: 583840 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2487. Min Act: -0.0000

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2439. Min Act: -0.0000

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1314142 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2283. Min Act: -0.0000

Data Index: 967261 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2420. Min Act: -0.0000

Data Index: 46765 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2318. Min Act: -0.0000

Data Index: 271178 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2280. Min Act: -0.0000

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2258. Min Act: -0.0000

Data Index: 260050 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1330911 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.3613. Min Range: -0.3613

Max Act: 0.2285. Min Act: -0.0001

Data Index: 1143761 (C4 (Web Text))

Max Activating Token Index: 315