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

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

Neuron 1971 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0001

Data Index: 965100 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0155. Min Act: -0.0001

Data Index: 920181 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1347648 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0001

Data Index: 548755 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0001

Data Index: 302272 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0001

Data Index: 471181 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0001

Data Index: 764595 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1233505 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0001

Data Index: 1083001 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0001

Data Index: 636242 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0001

Data Index: 425221 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0001

Data Index: 939107 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0001

Data Index: 1089913 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0001

Data Index: 144105 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1489316 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0001

Data Index: 38369 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0001

Data Index: 1423064 (Python Code)

Max Activating Token Index: 805

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0001

Data Index: 1081807 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0116. Min Act: -0.0001

Data Index: 928018 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0001

Data Index: 767497 (C4 (Web Text))

Max Activating Token Index: 10