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

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

Neuron 1919 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0132. Min Act: -0.0006

Data Index: 278284 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0130. Min Act: -0.0006

Data Index: 838875 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0006

Data Index: 747554 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0005

Data Index: 621108 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0116. Min Act: -0.0006

Data Index: 148768 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1041728 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0006

Data Index: 536171 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0006

Data Index: 35192 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0110. Min Act: -0.0005

Data Index: 714373 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0006

Data Index: 70086 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0106. Min Act: -0.0005

Data Index: 205979 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0006

Data Index: 304584 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0113. Min Act: -0.0006

Data Index: 749632 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1152523 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0105. Min Act: -0.0006

Data Index: 703518 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1174257 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1424118 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0005

Data Index: 513024 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1305218 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0109. Min Act: -0.0005

Data Index: 141856 (C4 (Web Text))

Max Activating Token Index: 474