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

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

Neuron 996 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0093. Min Range: -1.0093

Max Act: 1.0093. Min Act: -0.0000

Data Index: 235884 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9631. Min Act: -0.0000

Data Index: 752683 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9370. Min Act: -0.0000

Data Index: 974505 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8355. Min Act: -0.0000

Data Index: 989515 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1082841 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8297. Min Act: -0.0000

Data Index: 535806 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8286. Min Act: -0.0000

Data Index: 263784 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8412. Min Act: -0.0000

Data Index: 522985 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7801. Min Act: -0.0000

Data Index: 499150 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1047384 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8233. Min Act: -0.0000

Data Index: 525828 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7620. Min Act: -0.0000

Data Index: 444790 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1206016 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7620. Min Act: -0.0000

Data Index: 563515 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7442. Min Act: -0.0000

Data Index: 814325 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7208. Min Act: -0.0000

Data Index: 482054 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6965. Min Act: -0.0000

Data Index: 378269 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6396. Min Act: -0.0000

Data Index: 40456 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7300. Min Act: -0.0000

Data Index: 887793 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.6926. Min Act: -0.0000

Data Index: 234010 (C4 (Web Text))

Max Activating Token Index: 670