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

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

Neuron 4345 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: 0.7081. Min Range: -0.7081

Max Act: 0.7029. Min Act: -0.0000

Data Index: 235417 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1295109 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1235472 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6029. Min Act: -0.0000

Data Index: 441095 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.6256. Min Act: -0.0000

Data Index: 423763 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5498. Min Act: -0.0000

Data Index: 785700 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5657. Min Act: -0.0000

Data Index: 585031 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5814. Min Act: -0.0000

Data Index: 593995 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1045798 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5332. Min Act: -0.0000

Data Index: 564213 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5866. Min Act: -0.0000

Data Index: 950760 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5305. Min Act: -0.0000

Data Index: 336770 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1285167 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5470. Min Act: -0.0000

Data Index: 998345 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1119776 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5231. Min Act: -0.0000

Data Index: 103360 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5393. Min Act: -0.0000

Data Index: 53776 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1212630 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1054236 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.7081. Min Range: -0.7081

Max Act: 0.5641. Min Act: -0.0000

Data Index: 980561 (C4 (Web Text))

Max Activating Token Index: 173