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

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

Neuron 2347 in Layer 1

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: 2.0219. Min Range: -2.0219

Max Act: 2.0219. Min Act: -0.0002

Data Index: 20510 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.9600. Min Act: -0.0002

Data Index: 1331587 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8602. Min Act: -0.0002

Data Index: 664315 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8409. Min Act: -0.0002

Data Index: 660843 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8358. Min Act: -0.0002

Data Index: 379275 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8022. Min Act: -0.0003

Data Index: 591650 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8174. Min Act: -0.0002

Data Index: 649424 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8022. Min Act: -0.0002

Data Index: 954340 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8102. Min Act: -0.0002

Data Index: 970972 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7918. Min Act: -0.0002

Data Index: 1189882 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8092. Min Act: -0.0002

Data Index: 331611 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7964. Min Act: -0.0002

Data Index: 1290562 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7596. Min Act: -0.0002

Data Index: 567572 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7609. Min Act: -0.0002

Data Index: 26015 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7875. Min Act: -0.0002

Data Index: 320340 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7705. Min Act: -0.0003

Data Index: 1319396 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.8232. Min Act: -0.0002

Data Index: 608081 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7897. Min Act: -0.0002

Data Index: 1264855 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7761. Min Act: -0.0002

Data Index: 549191 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 2.0219. Min Range: -2.0219

Max Act: 1.7665. Min Act: -0.0002

Data Index: 145279 (C4 (Web Text))

Max Activating Token Index: 335