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

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

Neuron 5266 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7396. Min Range: -2.7396

Max Act: 2.5595. Min Act: -0.0000

Data Index: 276581 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 2.7396. Min Range: -2.7396

Max Act: 2.7396. Min Act: -0.0000

Data Index: 216220 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1413388 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.7656. Min Act: -0.0000

Data Index: 430458 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.7143. Min Act: -0.0000

Data Index: 1592922 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1388984 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.5963. Min Act: -0.0000

Data Index: 281290 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.7689. Min Act: -0.0000

Data Index: 854033 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.8107. Min Act: -0.0000

Data Index: 354601 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.8472. Min Act: -0.0000

Data Index: 1363175 (Python Code)

Max Activating Token Index: 813

Text #10

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.6546. Min Act: -0.0000

Data Index: 1629081 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1583066 (Python Code)

Max Activating Token Index: 238

Text #12

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.5725. Min Act: -0.0000

Data Index: 791839 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.6929. Min Act: -0.0000

Data Index: 676191 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.6906. Min Act: -0.0000

Data Index: 815682 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.5037. Min Act: -0.0000

Data Index: 409546 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.5705. Min Act: -0.0000

Data Index: 628495 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.6419. Min Act: -0.0000

Data Index: 1494226 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.5683. Min Act: -0.0000

Data Index: 910331 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 2.7396. Min Range: -2.7396

Max Act: 1.5560. Min Act: -0.0000

Data Index: 684626 (C4 (Web Text))

Max Activating Token Index: 195