Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 866 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.3547. Min Act: -0.0000

Data Index: 21896 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.3254. Min Act: -0.0000

Data Index: 866081 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.3330. Min Act: -0.0000

Data Index: 943171 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1052380 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2775. Min Act: -0.0000

Data Index: 157211 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2627. Min Act: -0.0000

Data Index: 948241 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1216528 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1441615 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2790. Min Act: -0.0000

Data Index: 735347 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2929. Min Act: -0.0000

Data Index: 304056 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2718. Min Act: -0.0000

Data Index: 709158 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2647. Min Act: -0.0000

Data Index: 668910 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2550. Min Act: -0.0000

Data Index: 516633 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2437. Min Act: -0.0000

Data Index: 433472 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2284. Min Act: -0.0000

Data Index: 196971 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1177045 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1321949 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2335. Min Act: -0.0000

Data Index: 394905 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2361. Min Act: -0.0000

Data Index: 303196 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.3547. Min Range: -0.3547

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1242087 (C4 (Web Text))

Max Activating Token Index: 713