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

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

Neuron 2896 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: 0.7365. Min Range: -0.7365

Max Act: 0.7365. Min Act: -0.0002

Data Index: 1217010 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7078. Min Act: -0.0003

Data Index: 120605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6874. Min Act: -0.0002

Data Index: 497765 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6744. Min Act: -0.0002

Data Index: 756106 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6667. Min Act: -0.0003

Data Index: 233276 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6520. Min Act: -0.0002

Data Index: 1087636 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6388. Min Act: -0.0002

Data Index: 364133 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6506. Min Act: -0.0002

Data Index: 537738 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6520. Min Act: -0.0002

Data Index: 1207068 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6362. Min Act: -0.0002

Data Index: 924023 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6147. Min Act: -0.0002

Data Index: 627772 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6367. Min Act: -0.0002

Data Index: 591408 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6352. Min Act: -0.0002

Data Index: 404705 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6097. Min Act: -0.0002

Data Index: 1100457 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6248. Min Act: -0.0003

Data Index: 396318 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6103. Min Act: -0.0002

Data Index: 239866 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.5983. Min Act: -0.0002

Data Index: 295011 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6013. Min Act: -0.0002

Data Index: 919955 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.5908. Min Act: -0.0002

Data Index: 627537 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6104. Min Act: -0.0002

Data Index: 213811 (C4 (Web Text))

Max Activating Token Index: 639