Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 985 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.1087. Min Range: -3.1087

Max Act: 3.1087. Min Act: -0.0000

Data Index: 1361085 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.7740. Min Act: -0.0000

Data Index: 1635718 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.5137. Min Act: 0.0000

Data Index: 1937905 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.4766. Min Act: -0.0000

Data Index: 513893 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.6925. Min Act: -0.0000

Data Index: 1462575 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.7936. Min Act: -0.0000

Data Index: 1976827 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.6450. Min Act: -0.0000

Data Index: 1908770 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.4850. Min Act: -0.0000

Data Index: 1001406 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.6250. Min Act: -0.0000

Data Index: 1001508 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.6992. Min Act: -0.0000

Data Index: 182422 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.1135. Min Act: -0.0000

Data Index: 904355 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.5584. Min Act: -0.0000

Data Index: 819372 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.6771. Min Act: -0.0000

Data Index: 1300888 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.5369. Min Act: -0.0000

Data Index: 888102 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.5163. Min Act: -0.0000

Data Index: 576474 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.8829. Min Act: -0.0000

Data Index: 1785160 (The Pile)

Max Activating Token Index: 558

Text #16

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.4057. Min Act: -0.0000

Data Index: 1268207 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.3798. Min Act: -0.0000

Data Index: 1416634 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.5000. Min Act: 0.0001

Data Index: 1684301 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 3.1087. Min Range: -3.1087

Max Act: 2.3919. Min Act: -0.0000

Data Index: 483115 (The Pile)

Max Activating Token Index: 978