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

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

Neuron 3301 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3856. Min Range: -2.3856

Max Act: 2.3856. Min Act: -0.0000

Data Index: 15345 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.3856. Min Range: -2.3856

Max Act: 2.0416. Min Act: -0.0000

Data Index: 855667 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 2.3856. Min Range: -2.3856

Max Act: 2.0346. Min Act: -0.0000

Data Index: 583640 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.9727. Min Act: -0.0000

Data Index: 264624 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.9777. Min Act: -0.0000

Data Index: 541590 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1003162 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.8789. Min Act: -0.0000

Data Index: 349088 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5589. Min Act: -0.0000

Data Index: 104897 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6628. Min Act: -0.0000

Data Index: 967299 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1320277 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6181. Min Act: -0.0000

Data Index: 1387034 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5253. Min Act: -0.0000

Data Index: 1114945 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1144360 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5377. Min Act: -0.0000

Data Index: 1458307 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5107. Min Act: -0.0000

Data Index: 855647 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.7055. Min Act: -0.0000

Data Index: 30066 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6895. Min Act: -0.0000

Data Index: 922925 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6069. Min Act: -0.0000

Data Index: 31422 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1444694 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 2.3856. Min Range: -2.3856

Max Act: 1.6844. Min Act: -0.0000

Data Index: 650822 (C4 (Web Text))

Max Activating Token Index: 918