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

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

Neuron 1259 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: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1451404 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0140. Min Act: -0.0001

Data Index: 807583 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1574169 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0135. Min Act: -0.0001

Data Index: 570028 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0001

Data Index: 293689 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0001

Data Index: 217931 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0001

Data Index: 78738 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0001

Data Index: 104031 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0001

Data Index: 240710 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0001

Data Index: 1400292 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1349878 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1453382 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0001

Data Index: 519199 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0001

Data Index: 5357 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0001

Data Index: 1273088 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0001

Data Index: 112180 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0128. Min Act: -0.0001

Data Index: 1223258 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0001

Data Index: 433679 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0001

Data Index: 266900 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0001

Data Index: 594859 (C4 (Web Text))

Max Activating Token Index: 105