Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5818 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.5100. Min Act: -0.0000

Data Index: 1285957 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.4233. Min Act: -0.0000

Data Index: 176229 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.3914. Min Act: -0.0000

Data Index: 880338 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.2316. Min Act: -0.0000

Data Index: 1049822 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.2792. Min Act: -0.0000

Data Index: 1035715 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.2523. Min Act: -0.0000

Data Index: 686939 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.1120. Min Act: -0.0000

Data Index: 1275352 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.2151. Min Act: -0.0000

Data Index: 593240 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.0469. Min Act: -0.0000

Data Index: 1314502 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.1318. Min Act: -0.0000

Data Index: 417920 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.0956. Min Act: -0.0000

Data Index: 885427 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.0676. Min Act: -0.0000

Data Index: 996953 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.0393. Min Act: -0.0000

Data Index: 1038605 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 2.5100. Min Range: -2.5100

Max Act: 1.9583. Min Act: -0.0000

Data Index: 848771 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 2.5100. Min Range: -2.5100

Max Act: 1.9370. Min Act: -0.0000

Data Index: 1211617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.1424. Min Act: -0.0000

Data Index: 1106877 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 2.5100. Min Range: -2.5100

Max Act: 1.9062. Min Act: -0.0000

Data Index: 502749 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.0109. Min Act: -0.0000

Data Index: 1018837 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.1026. Min Act: -0.0000

Data Index: 723218 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 2.5100. Min Range: -2.5100

Max Act: 2.0780. Min Act: -0.0000

Data Index: 329810 (C4 (Web Text))

Max Activating Token Index: 576