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

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

Neuron 1955 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.4910. Min Act: -0.0001

Data Index: 457936 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.6050. Min Act: -0.0000

Data Index: 487750 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.4579. Min Act: -0.0000

Data Index: 367273 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.3720. Min Act: -0.0000

Data Index: 37010 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1198196 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.3171. Min Act: -0.0000

Data Index: 10733 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.2028. Min Act: -0.0000

Data Index: 733361 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.1987. Min Act: -0.0000

Data Index: 976283 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.2139. Min Act: -0.0000

Data Index: 937694 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.2933. Min Act: -0.0000

Data Index: 232352 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.2683. Min Act: -0.0000

Data Index: 853564 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.1916. Min Act: -0.0000

Data Index: 1067614 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.2885. Min Act: -0.0000

Data Index: 91036 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 2.6050. Min Range: -2.6050

Max Act: 2.0453. Min Act: -0.0000

Data Index: 1338788 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 2.6050. Min Range: -2.6050

Max Act: 1.9929. Min Act: -0.0000

Data Index: 1050734 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 2.6050. Min Range: -2.6050

Max Act: 1.9801. Min Act: -0.0000

Data Index: 271902 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.6050. Min Range: -2.6050

Max Act: 1.7657. Min Act: -0.0000

Data Index: 274106 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 2.6050. Min Range: -2.6050

Max Act: 1.4043. Min Act: -0.0000

Data Index: 691 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 2.6050. Min Range: -2.6050

Max Act: 1.6719. Min Act: -0.0000

Data Index: 148733 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 2.6050. Min Range: -2.6050

Max Act: 1.5843. Min Act: -0.0000

Data Index: 437172 (C4 (Web Text))

Max Activating Token Index: 101