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

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

Neuron 1701 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.3137. Min Act: -0.0000

Data Index: 278947 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2929. Min Act: -0.0000

Data Index: 200877 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2805. Min Act: -0.0000

Data Index: 824448 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2806. Min Act: -0.0000

Data Index: 643005 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2740. Min Act: -0.0000

Data Index: 187022 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2756. Min Act: -0.0000

Data Index: 517060 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1110938 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2401. Min Act: -0.0000

Data Index: 473079 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2479. Min Act: -0.0000

Data Index: 842061 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2287. Min Act: -0.0000

Data Index: 671489 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2325. Min Act: -0.0000

Data Index: 491838 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2341. Min Act: -0.0000

Data Index: 548332 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1086792 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2084. Min Act: -0.0000

Data Index: 302394 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2081. Min Act: -0.0000

Data Index: 602197 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2247. Min Act: -0.0000

Data Index: 383006 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1296692 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1018679 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1351929 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.3137. Min Range: -0.3137

Max Act: 0.2186. Min Act: 0.0000

Data Index: 1341681 (C4 (Web Text))

Max Activating Token Index: 321