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

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

Neuron 1223 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: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0001

Data Index: 526356 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0177. Min Act: -0.0001

Data Index: 689071 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0176. Min Act: -0.0001

Data Index: 586574 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1265784 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1068080 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0167. Min Act: -0.0001

Data Index: 331678 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0162. Min Act: -0.0001

Data Index: 770062 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0167. Min Act: -0.0001

Data Index: 774140 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0164. Min Act: -0.0001

Data Index: 361285 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1302203 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0161. Min Act: -0.0001

Data Index: 174651 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0162. Min Act: -0.0001

Data Index: 930333 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0162. Min Act: -0.0001

Data Index: 481992 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1226142 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1131896 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0158. Min Act: -0.0001

Data Index: 164945 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0157. Min Act: -0.0001

Data Index: 810931 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0155. Min Act: -0.0001

Data Index: 905582 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0157. Min Act: -0.0001

Data Index: 137938 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0157. Min Act: -0.0001

Data Index: 962706 (C4 (Web Text))

Max Activating Token Index: 539