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

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

Neuron 62 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: 1.0099. Min Range: -1.0099

Max Act: 1.0099. Min Act: -0.0001

Data Index: 1595142 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1418351 (Python Code)

Max Activating Token Index: 504

Text #2

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1392066 (Python Code)

Max Activating Token Index: 86

Text #3

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1547719 (Python Code)

Max Activating Token Index: 525

Text #4

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1501630 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1369495 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1593019 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1427728 (Python Code)

Max Activating Token Index: 207

Text #8

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1498472 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1392615 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1557394 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1406917 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1436560 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1457357 (Python Code)

Max Activating Token Index: 116

Text #14

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1418083 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1361347 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1408605 (Python Code)

Max Activating Token Index: 429

Text #17

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1532810 (Python Code)

Max Activating Token Index: 972

Text #18

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1458066 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.0099. Min Range: -1.0099

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1627064 (Python Code)

Max Activating Token Index: 36