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

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

Neuron 276 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.4788. Min Act: -0.0000

Data Index: 866559 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6856. Min Act: -0.0000

Data Index: 833153 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6385. Min Act: -0.0000

Data Index: 471306 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5437. Min Act: -0.0000

Data Index: 124469 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.3808. Min Act: -0.0000

Data Index: 518444 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.0993. Min Act: -0.0000

Data Index: 744318 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.0055. Min Act: -0.0000

Data Index: 1335942 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.8203. Min Act: -0.0000

Data Index: 1118439 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.9219. Min Act: -0.0000

Data Index: 1007375 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.7009. Min Act: -0.0000

Data Index: 440095 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.6276. Min Act: -0.0000

Data Index: 1061651 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.6147. Min Act: -0.0000

Data Index: 1008294 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.5703. Min Act: -0.0000

Data Index: 765395 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.6824. Min Act: -0.0000

Data Index: 1096061 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.2140. Min Act: -0.0000

Data Index: 527217 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.5069. Min Act: -0.0000

Data Index: 577701 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.4241. Min Act: -0.0000

Data Index: 820950 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.2026. Min Act: -0.0000

Data Index: 17487 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.1793. Min Act: -0.0000

Data Index: 104497 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 4.6856. Min Range: -4.6856

Max Act: 3.0087. Min Act: -0.0000

Data Index: 646638 (C4 (Web Text))

Max Activating Token Index: 316