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

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

Neuron 789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2963. Min Range: -2.2963

Max Act: 2.2963. Min Act: -0.0000

Data Index: 192571 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 2.2963. Min Range: -2.2963

Max Act: 2.2472. Min Act: -0.0000

Data Index: 698491 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.8062. Min Act: -0.0000

Data Index: 1328630 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.7936. Min Act: -0.0000

Data Index: 197868 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.7848. Min Act: -0.0000

Data Index: 1277423 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.7347. Min Act: -0.0000

Data Index: 177842 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1172754 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4927. Min Act: -0.0000

Data Index: 937455 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.6332. Min Act: -0.0000

Data Index: 900525 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.5710. Min Act: -0.0000

Data Index: 561262 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.6208. Min Act: -0.0000

Data Index: 1312521 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4835. Min Act: -0.0000

Data Index: 338827 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1025849 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1338025 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.5043. Min Act: -0.0000

Data Index: 239143 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4894. Min Act: -0.0000

Data Index: 506265 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4656. Min Act: -0.0000

Data Index: 918323 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1256888 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.4644. Min Act: -0.0000

Data Index: 1082919 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 2.2963. Min Range: -2.2963

Max Act: 1.3618. Min Act: -0.0000

Data Index: 280389 (C4 (Web Text))

Max Activating Token Index: 462