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

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

Neuron 3716 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5478. Min Act: -0.0000

Data Index: 144304 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1057989 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1195445 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5197. Min Act: -0.0000

Data Index: 173285 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5056. Min Act: -0.0000

Data Index: 702020 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4956. Min Act: -0.0000

Data Index: 892878 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4746. Min Act: -0.0000

Data Index: 754167 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4912. Min Act: -0.0000

Data Index: 368154 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4639. Min Act: -0.0000

Data Index: 689393 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4415. Min Act: -0.0000

Data Index: 901296 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4525. Min Act: -0.0000

Data Index: 904414 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4516. Min Act: -0.0000

Data Index: 182368 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4491. Min Act: -0.0000

Data Index: 863798 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4423. Min Act: -0.0000

Data Index: 452761 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4362. Min Act: -0.0000

Data Index: 646645 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4366. Min Act: -0.0000

Data Index: 440587 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1118677 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1040106 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.6058. Min Range: -0.6058

Max Act: 0.4368. Min Act: -0.0000

Data Index: 374232 (C4 (Web Text))

Max Activating Token Index: 673