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

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

Neuron 616 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: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0006

Data Index: 970585 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0125. Min Act: -0.0006

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0118. Min Act: -0.0006

Data Index: 629850 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0109. Min Act: -0.0006

Data Index: 189203 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0103. Min Act: -0.0006

Data Index: 448835 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0107. Min Act: -0.0006

Data Index: 423600 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0108. Min Act: -0.0006

Data Index: 38634 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0104. Min Act: -0.0006

Data Index: 982616 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0101. Min Act: -0.0006

Data Index: 119875 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0101. Min Act: -0.0006

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0099. Min Act: -0.0006

Data Index: 759911 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1215198 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0093. Min Act: -0.0006

Data Index: 233290 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0095. Min Act: -0.0006

Data Index: 758734 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0096. Min Act: -0.0006

Data Index: 330650 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0094. Min Act: -0.0006

Data Index: 568838 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1192311 (C4 (Web Text))

Max Activating Token Index: 190