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

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

Neuron 3315 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0596. Min Range: -1.0596

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1583046 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1627643 (Python Code)

Max Activating Token Index: 721

Text #2

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.9347. Min Act: -0.0001

Data Index: 1627044 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8256. Min Act: -0.0001

Data Index: 1648251 (Python Code)

Max Activating Token Index: 746

Text #4

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7996. Min Act: -0.0001

Data Index: 1656290 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1468160 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1602533 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7981. Min Act: -0.0001

Data Index: 1480555 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7524. Min Act: -0.0001

Data Index: 1384304 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1467157 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7805. Min Act: -0.0001

Data Index: 1449949 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7428. Min Act: -0.0001

Data Index: 1449482 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1399170 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1618360 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1485293 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1402532 (Python Code)

Max Activating Token Index: 812

Text #16

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1628781 (Python Code)

Max Activating Token Index: 447

Text #17

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1384440 (Python Code)

Max Activating Token Index: 271

Text #18

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1389705 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 1.0596. Min Range: -1.0596

Max Act: 0.7077. Min Act: -0.0001

Data Index: 1555846 (Python Code)

Max Activating Token Index: 129