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

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

Neuron 2824 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0002

Data Index: 701681 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0113. Min Act: -0.0002

Data Index: 936814 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0107. Min Act: -0.0002

Data Index: 15639 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0002

Data Index: 192898 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1483988 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0102. Min Act: -0.0002

Data Index: 44410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0100. Min Act: -0.0002

Data Index: 155087 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0097. Min Act: -0.0002

Data Index: 514301 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1618060 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0096. Min Act: -0.0002

Data Index: 502578 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0002

Data Index: 111188 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1086011 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0002

Data Index: 894497 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1252410 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1438315 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1491340 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0088. Min Act: -0.0002

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1195262 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0089. Min Act: -0.0002

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 226