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

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

Neuron 2988 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4014. Min Range: -2.4014

Max Act: 2.4014. Min Act: -0.0000

Data Index: 447850 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.6115. Min Act: -0.0000

Data Index: 362323 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.5416. Min Act: -0.0000

Data Index: 940643 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.4938. Min Act: -0.0000

Data Index: 571887 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1164401 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.3398. Min Act: -0.0000

Data Index: 619873 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.2445. Min Act: -0.0000

Data Index: 360951 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1383. Min Act: -0.0000

Data Index: 63496 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.2612. Min Act: -0.0000

Data Index: 49998 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1563. Min Act: -0.0000

Data Index: 974637 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1780. Min Act: -0.0000

Data Index: 848112 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.0890. Min Act: -0.0000

Data Index: 169120 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.2161. Min Act: -0.0000

Data Index: 689039 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.2063. Min Act: -0.0000

Data Index: 471614 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1096. Min Act: -0.0000

Data Index: 545483 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1336252 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.0387. Min Act: -0.0000

Data Index: 561266 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1116238 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 2.4014. Min Range: -2.4014

Max Act: 0.9937. Min Act: -0.0000

Data Index: 842245 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 2.4014. Min Range: -2.4014

Max Act: 1.1544. Min Act: -0.0000

Data Index: 905351 (C4 (Web Text))

Max Activating Token Index: 630