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

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

Neuron 3676 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1466480 (Python Code)

Max Activating Token Index: 595

Text #1

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1351336 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1594968 (Python Code)

Max Activating Token Index: 950

Text #3

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3428. Min Act: -0.0000

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1378712 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1565629 (Python Code)

Max Activating Token Index: 898

Text #6

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1434131 (Python Code)

Max Activating Token Index: 385

Text #7

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2939. Min Act: -0.0000

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1368966 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3044. Min Act: -0.0000

Data Index: 853286 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1432249 (Python Code)

Max Activating Token Index: 768

Text #11

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3190. Min Act: -0.0000

Data Index: 18051 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2580. Min Act: -0.0000

Data Index: 243213 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2558. Min Act: -0.0000

Data Index: 104446 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1566914 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1474169 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1481265 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1455230 (Python Code)

Max Activating Token Index: 402

Text #18

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1399909 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.2456. Min Act: -0.0000

Data Index: 875348 (C4 (Web Text))

Max Activating Token Index: 929