Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2812. Min Range: -5.2812

Max Act: 5.2812. Min Act: -0.0000

Data Index: 722510 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.9637. Min Act: -0.0000

Data Index: 1180130 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.5441. Min Act: -0.0000

Data Index: 619186 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.5361. Min Act: -0.0000

Data Index: 41031 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.5798. Min Act: -0.0000

Data Index: 1235235 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.6674. Min Act: -0.0000

Data Index: 476607 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.5363. Min Act: -0.0000

Data Index: 1343346 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.0156. Min Act: -0.0000

Data Index: 28579 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.1746. Min Act: -0.0000

Data Index: 66398 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.0850. Min Act: -0.0000

Data Index: 599598 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.0410. Min Act: -0.0000

Data Index: 538249 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.1635. Min Act: -0.0000

Data Index: 1268843 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.9328. Min Act: -0.0000

Data Index: 640081 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 5.2812. Min Range: -5.2812

Max Act: 4.2172. Min Act: -0.0000

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.8840. Min Act: -0.0000

Data Index: 787167 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.8698. Min Act: -0.0000

Data Index: 157469 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.8150. Min Act: -0.0000

Data Index: 481789 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.8136. Min Act: -0.0000

Data Index: 382206 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.7880. Min Act: -0.0000

Data Index: 191737 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 5.2812. Min Range: -5.2812

Max Act: 3.6523. Min Act: -0.0000

Data Index: 1317296 (C4 (Web Text))

Max Activating Token Index: 785