Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1346 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0006

Data Index: 492841 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0120. Min Act: -0.0006

Data Index: 963860 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0115. Min Act: -0.0006

Data Index: 8432 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0114. Min Act: -0.0006

Data Index: 787576 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0112. Min Act: -0.0006

Data Index: 512722 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0114. Min Act: -0.0006

Data Index: 964502 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0006

Data Index: 135595 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1127460 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0111. Min Act: -0.0006

Data Index: 566427 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0110. Min Act: -0.0006

Data Index: 410892 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0006

Data Index: 366731 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0006

Data Index: 822890 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0006

Data Index: 37659 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1085357 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0109. Min Act: -0.0006

Data Index: 882299 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1142398 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1534072 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0006

Data Index: 252681 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0108. Min Act: -0.0006

Data Index: 517297 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0120. Min Range: -0.0120

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1150144 (C4 (Web Text))

Max Activating Token Index: 257