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

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

Neuron 2503 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: 1.0366. Min Range: -1.0366

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1145139 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.0366. Min Range: -1.0366

Max Act: 1.0366. Min Act: -0.0000

Data Index: 299878 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1344235 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7956. Min Act: -0.0000

Data Index: 160166 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7758. Min Act: -0.0000

Data Index: 954407 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7541. Min Act: -0.0000

Data Index: 348384 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7014. Min Act: -0.0000

Data Index: 96947 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6611. Min Act: -0.0000

Data Index: 718532 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6809. Min Act: -0.0000

Data Index: 17912 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6562. Min Act: -0.0000

Data Index: 264386 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6292. Min Act: -0.0000

Data Index: 261872 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6180. Min Act: -0.0000

Data Index: 331510 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6063. Min Act: -0.0000

Data Index: 144175 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1160422 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5660. Min Act: -0.0000

Data Index: 353257 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1145061 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1130123 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5888. Min Act: -0.0000

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1028513 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1207183 (C4 (Web Text))

Max Activating Token Index: 916