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

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

Neuron 1440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.3601. Min Act: -0.0000

Data Index: 87686 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.2900. Min Act: -0.0000

Data Index: 140400 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.3010. Min Act: -0.0000

Data Index: 645980 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.2761. Min Act: -0.0000

Data Index: 813043 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.2427. Min Act: -0.0000

Data Index: 474856 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.1283. Min Act: -0.0000

Data Index: 92865 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.2449. Min Act: -0.0000

Data Index: 412238 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.2723. Min Act: -0.0000

Data Index: 315148 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0964. Min Act: -0.0000

Data Index: 114276 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.1225. Min Act: -0.0000

Data Index: 812393 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1293804 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.1989. Min Act: -0.0000

Data Index: 970990 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1240216 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1096209 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.1146. Min Act: -0.0000

Data Index: 580746 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0678. Min Act: -0.0000

Data Index: 698022 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.1352. Min Act: -0.0000

Data Index: 836710 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0337. Min Act: -0.0000

Data Index: 592331 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0625. Min Act: -0.0000

Data Index: 357518 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.3601. Min Range: -1.3601

Max Act: 1.0855. Min Act: -0.0000

Data Index: 206679 (C4 (Web Text))

Max Activating Token Index: 338