Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5477. Min Act: -0.0001

Data Index: 1384791 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5011. Min Act: -0.0001

Data Index: 339920 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4964. Min Act: -0.0000

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4843. Min Act: -0.0000

Data Index: 654849 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4647. Min Act: -0.0001

Data Index: 227345 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4530. Min Act: -0.0000

Data Index: 892264 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4371. Min Act: -0.0001

Data Index: 1564033 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4453. Min Act: -0.0000

Data Index: 739016 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4343. Min Act: -0.0001

Data Index: 137508 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1620075 (Python Code)

Max Activating Token Index: 343

Text #10

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1168620 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4330. Min Act: -0.0000

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4430. Min Act: -0.0000

Data Index: 616638 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4224. Min Act: -0.0001

Data Index: 20335 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4179. Min Act: -0.0001

Data Index: 1497171 (Python Code)

Max Activating Token Index: 75

Text #15

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4282. Min Act: -0.0001

Data Index: 1652340 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4171. Min Act: -0.0000

Data Index: 197225 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1395768 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3816. Min Act: -0.0000

Data Index: 586503 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1364245 (Python Code)

Max Activating Token Index: 504