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

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

Neuron 2574 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: 1.9198. Min Range: -1.9198

Max Act: 1.9198. Min Act: -0.0000

Data Index: 438749 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.8338. Min Act: -0.0000

Data Index: 724994 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.8679. Min Act: -0.0000

Data Index: 448930 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.7092. Min Act: -0.0000

Data Index: 467059 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.6984. Min Act: -0.0000

Data Index: 462925 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.6580. Min Act: -0.0000

Data Index: 429132 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.5324. Min Act: -0.0000

Data Index: 935573 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.7203. Min Act: -0.0000

Data Index: 224822 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1038856 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4583. Min Act: -0.0000

Data Index: 304046 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.5322. Min Act: -0.0000

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1254462 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.5151. Min Act: -0.0000

Data Index: 262626 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.5113. Min Act: -0.0000

Data Index: 441994 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4141. Min Act: -0.0000

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4878. Min Act: -0.0000

Data Index: 697598 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1093803 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1439987 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4552. Min Act: -0.0000

Data Index: 625181 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.9198. Min Range: -1.9198

Max Act: 1.4410. Min Act: -0.0000

Data Index: 891862 (C4 (Web Text))

Max Activating Token Index: 827