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

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

Neuron 654 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: 0.4010. Min Range: -0.4010

Max Act: 0.4010. Min Act: -0.0001

Data Index: 773873 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3724. Min Act: -0.0001

Data Index: 532642 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1474458 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1551490 (Python Code)

Max Activating Token Index: 862

Text #4

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3177. Min Act: -0.0000

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1540216 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1403418 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1574426 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3002. Min Act: -0.0001

Data Index: 1641528 (Python Code)

Max Activating Token Index: 110

Text #9

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1637608 (Python Code)

Max Activating Token Index: 772

Text #10

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3090. Min Act: -0.0000

Data Index: 964517 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3165. Min Act: -0.0001

Data Index: 1566371 (Python Code)

Max Activating Token Index: 754

Text #12

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2941. Min Act: -0.0001

Data Index: 73917 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2844. Min Act: -0.0000

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1464380 (Python Code)

Max Activating Token Index: 621

Text #15

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2916. Min Act: -0.0000

Data Index: 520036 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2863. Min Act: -0.0000

Data Index: 132902 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1467624 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2792. Min Act: -0.0000

Data Index: 412941 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2710. Min Act: -0.0001

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 823