Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 958 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0002

Data Index: 244282 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0002

Data Index: 726414 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0133. Min Act: -0.0002

Data Index: 107269 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0135. Min Act: -0.0002

Data Index: 793466 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0127. Min Act: -0.0002

Data Index: 68006 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1342058 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1226241 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0002

Data Index: 716292 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0127. Min Act: -0.0002

Data Index: 58751 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1209358 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0002

Data Index: 300972 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1345591 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0002

Data Index: 368607 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0002

Data Index: 819788 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 864791 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1198963 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 147384 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 308663 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0123. Min Act: -0.0002

Data Index: 829636 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1154489 (C4 (Web Text))

Max Activating Token Index: 231