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

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

Neuron 1297 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1050412 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4863. Min Act: -0.0000

Data Index: 270809 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1254753 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4573. Min Act: -0.0000

Data Index: 23936 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4489. Min Act: -0.0000

Data Index: 37282 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1344004 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4294. Min Act: -0.0000

Data Index: 482877 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4342. Min Act: -0.0000

Data Index: 74352 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4554. Min Act: -0.0000

Data Index: 435985 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4242. Min Act: -0.0000

Data Index: 888724 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3950. Min Act: -0.0000

Data Index: 660888 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4159. Min Act: -0.0000

Data Index: 843743 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4048. Min Act: -0.0000

Data Index: 563414 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4001. Min Act: -0.0000

Data Index: 744057 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3970. Min Act: -0.0000

Data Index: 317384 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1129690 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4054. Min Act: -0.0000

Data Index: 989655 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1000097 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3868. Min Act: -0.0000

Data Index: 850687 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3845. Min Act: -0.0000

Data Index: 92546 (C4 (Web Text))

Max Activating Token Index: 239