Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.4820. Min Act: -0.0004

Data Index: 57760 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 3.4820. Min Range: -3.4820

Max Act: 3.3791. Min Act: -0.0004

Data Index: 1519857 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 3.4820. Min Range: -3.4820

Max Act: 2.1492. Min Act: -0.0004

Data Index: 1595696 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 3.4820. Min Range: -3.4820

Max Act: 2.0000. Min Act: -0.0003

Data Index: 1547847 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.4820. Min Range: -3.4820

Max Act: 1.4984. Min Act: -0.0003

Data Index: 1423838 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 3.4820. Min Range: -3.4820

Max Act: 1.2811. Min Act: -0.0004

Data Index: 1590192 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.9435. Min Act: -0.0004

Data Index: 277284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.7693. Min Act: -0.0004

Data Index: 761245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.5656. Min Act: -0.0004

Data Index: 700001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.5034. Min Act: -0.0004

Data Index: 1506290 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.4728. Min Act: -0.0004

Data Index: 828054 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.4122. Min Act: -0.0004

Data Index: 551631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.4053. Min Act: -0.0004

Data Index: 193632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3726. Min Act: -0.0004

Data Index: 1531712 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3726. Min Act: -0.0004

Data Index: 1181511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3630. Min Act: -0.0003

Data Index: 1459395 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3597. Min Act: -0.0004

Data Index: 999196 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3215. Min Act: -0.0004

Data Index: 291515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3244. Min Act: -0.0004

Data Index: 534382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.4820. Min Range: -3.4820

Max Act: 0.3203. Min Act: -0.0004

Data Index: 628338 (C4 (Web Text))

Max Activating Token Index: 1023