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

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

Neuron 879 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2865. Min Act: -0.0002

Data Index: 370131 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2935. Min Act: -0.0002

Data Index: 1252375 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2841. Min Act: -0.0002

Data Index: 1173879 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2804. Min Act: -0.0002

Data Index: 115065 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2860. Min Act: -0.0002

Data Index: 1069951 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0002

Data Index: 969518 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2841. Min Act: -0.0002

Data Index: 229905 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2766. Min Act: -0.0002

Data Index: 1195212 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2647. Min Act: -0.0002

Data Index: 1107371 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2871. Min Act: -0.0002

Data Index: 832411 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2881. Min Act: -0.0002

Data Index: 731767 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2664. Min Act: -0.0002

Data Index: 1188910 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2580. Min Act: -0.0002

Data Index: 351628 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2759. Min Act: -0.0002

Data Index: 745627 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2532. Min Act: -0.0002

Data Index: 809000 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2787. Min Act: -0.0002

Data Index: 1298757 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2670. Min Act: -0.0002

Data Index: 300634 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2917. Min Act: -0.0002

Data Index: 1053037 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2645. Min Act: -0.0002

Data Index: 600929 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2528. Min Act: -0.0002

Data Index: 1279447 (C4 (Web Text))

Max Activating Token Index: 575