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

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

Neuron 5727 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0791. Min Range: -4.0791

Max Act: 4.0791. Min Act: -0.0000

Data Index: 996845 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.8823. Min Act: -0.0000

Data Index: 540738 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.8113. Min Act: -0.0000

Data Index: 480433 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.5621. Min Act: -0.0000

Data Index: 269110 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.1894. Min Act: -0.0000

Data Index: 31702 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.1525. Min Act: -0.0000

Data Index: 13259 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.9597. Min Act: -0.0000

Data Index: 966238 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.2476. Min Act: -0.0000

Data Index: 1019611 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.3798. Min Act: -0.0000

Data Index: 827107 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.9284. Min Act: -0.0000

Data Index: 713960 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 4.0791. Min Range: -4.0791

Max Act: 3.0365. Min Act: -0.0000

Data Index: 913648 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.9945. Min Act: -0.0000

Data Index: 1199679 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.6970. Min Act: -0.0000

Data Index: 146900 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.3801. Min Act: -0.0000

Data Index: 1053896 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.4260. Min Act: -0.0000

Data Index: 305610 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.5416. Min Act: -0.0000

Data Index: 693804 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.1307. Min Act: -0.0000

Data Index: 851777 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.3663. Min Act: -0.0000

Data Index: 276149 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.4264. Min Act: -0.0000

Data Index: 414005 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 4.0791. Min Range: -4.0791

Max Act: 2.0362. Min Act: -0.0000

Data Index: 790644 (C4 (Web Text))

Max Activating Token Index: 759