Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0070. Min Act: -0.0003

Data Index: 303754 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1368412 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0065. Min Act: -0.0004

Data Index: 644851 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0063. Min Act: -0.0005

Data Index: 771546 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0063. Min Act: -0.0004

Data Index: 358136 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0062. Min Act: -0.0004

Data Index: 1169135 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0062. Min Act: -0.0004

Data Index: 271059 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0060. Min Act: -0.0004

Data Index: 371437 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0059. Min Act: -0.0004

Data Index: 823534 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0058. Min Act: -0.0004

Data Index: 1421588 (Python Code)

Max Activating Token Index: 843

Text #11

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0058. Min Act: -0.0004

Data Index: 852131 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0057. Min Act: -0.0004

Data Index: 728245 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0057. Min Act: -0.0004

Data Index: 158227 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1116405 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0055. Min Act: -0.0004

Data Index: 525343 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0055. Min Act: -0.0005

Data Index: 565477 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0055. Min Act: -0.0003

Data Index: 5600 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0054. Min Act: -0.0005

Data Index: 919283 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1082379 (C4 (Web Text))

Max Activating Token Index: 592