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

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

Neuron 216 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7066. Min Act: -0.0000

Data Index: 853547 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1269071 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7091. Min Act: -0.0000

Data Index: 900025 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1041105 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7738. Min Act: -0.0000

Data Index: 119480 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7023. Min Act: -0.0000

Data Index: 474011 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7171. Min Act: -0.0000

Data Index: 156884 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1303499 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6597. Min Act: -0.0000

Data Index: 697219 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6800. Min Act: -0.0000

Data Index: 384084 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1302120 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1173695 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1176232 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5720. Min Act: -0.0000

Data Index: 735024 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5749. Min Act: -0.0000

Data Index: 792216 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.6296. Min Act: -0.0000

Data Index: 54773 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5741. Min Act: -0.0000

Data Index: 463303 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1048548 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5611. Min Act: -0.0000

Data Index: 460259 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.7738. Min Range: -0.7738

Max Act: 0.5201. Min Act: -0.0000

Data Index: 461372 (C4 (Web Text))

Max Activating Token Index: 151