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

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

Neuron 6080 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1168887 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.1761. Min Act: -0.0000

Data Index: 644431 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.1680. Min Act: -0.0000

Data Index: 376850 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1281085 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1190225 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1358377 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1223398 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0137. Min Act: -0.0000

Data Index: 362228 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9671. Min Act: -0.0000

Data Index: 762349 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0679. Min Act: -0.0001

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1353575 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0036. Min Act: -0.0001

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1070729 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1004540 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9641. Min Act: -0.0001

Data Index: 248381 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9055. Min Act: -0.0000

Data Index: 925304 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9662. Min Act: -0.0000

Data Index: 336672 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.2005. Min Range: -1.2005

Max Act: 1.0049. Min Act: -0.0001

Data Index: 339267 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9439. Min Act: -0.0000

Data Index: 504013 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.2005. Min Range: -1.2005

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1317062 (C4 (Web Text))

Max Activating Token Index: 38