Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0000

Data Index: 1199327 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0140. Min Act: -0.0000

Data Index: 227197 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0135. Min Act: -0.0000

Data Index: 549908 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0128. Min Act: -0.0000

Data Index: 1076508 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0128. Min Act: -0.0000

Data Index: 1273916 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0130. Min Act: -0.0000

Data Index: 362994 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0130. Min Act: -0.0000

Data Index: 861343 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0119. Min Act: -0.0000

Data Index: 1627899 (Python Code)

Max Activating Token Index: 53

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0125. Min Act: -0.0000

Data Index: 701389 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0128. Min Act: -0.0000

Data Index: 360216 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0120. Min Act: -0.0000

Data Index: 566788 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0117. Min Act: -0.0000

Data Index: 563075 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0124. Min Act: -0.0000

Data Index: 678205 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1071747 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0121. Min Act: -0.0000

Data Index: 270449 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0118. Min Act: -0.0000

Data Index: 1575548 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0113. Min Act: -0.0000

Data Index: 867463 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0112. Min Act: -0.0000

Data Index: 1187582 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0099. Min Act: -0.0000

Data Index: 418703 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0109. Min Act: -0.0000

Data Index: 512469 (C4 (Web Text))

Max Activating Token Index: 82