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

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

Neuron 4002 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: 3.3091. Min Range: -3.3091

Max Act: 3.1717. Min Act: -0.0000

Data Index: 1302462 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.3091. Min Act: -0.0000

Data Index: 839 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.9770. Min Act: -0.0000

Data Index: 596383 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.3091. Min Range: -3.3091

Max Act: 3.0694. Min Act: -0.0000

Data Index: 82005 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.8731. Min Act: -0.0000

Data Index: 1051986 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.8473. Min Act: -0.0000

Data Index: 1067159 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.8343. Min Act: -0.0000

Data Index: 262118 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.6562. Min Act: -0.0000

Data Index: 1169502 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.6284. Min Act: -0.0000

Data Index: 1191851 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.7513. Min Act: -0.0000

Data Index: 1519437 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.6922. Min Act: -0.0000

Data Index: 578606 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.6498. Min Act: -0.0000

Data Index: 1454052 (Python Code)

Max Activating Token Index: 771

Text #12

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.4727. Min Act: -0.0000

Data Index: 1449199 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.5916. Min Act: -0.0000

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.5448. Min Act: -0.0000

Data Index: 1302883 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.5437. Min Act: -0.0000

Data Index: 1093756 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.5126. Min Act: -0.0000

Data Index: 880435 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.5015. Min Act: -0.0000

Data Index: 1088117 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.4249. Min Act: -0.0000

Data Index: 292603 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 3.3091. Min Range: -3.3091

Max Act: 2.4020. Min Act: -0.0000

Data Index: 816418 (C4 (Web Text))

Max Activating Token Index: 63