Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3657 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.9441. Min Act: -0.0001

Data Index: 996089 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.9012. Min Act: -0.0001

Data Index: 415015 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8998. Min Act: -0.0001

Data Index: 240151 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.9123. Min Act: -0.0001

Data Index: 351467 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8937. Min Act: -0.0001

Data Index: 544486 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8300. Min Act: -0.0001

Data Index: 1195208 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8481. Min Act: -0.0001

Data Index: 404788 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8457. Min Act: -0.0001

Data Index: 14130 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7912. Min Act: -0.0001

Data Index: 497346 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7862. Min Act: -0.0001

Data Index: 856460 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8042. Min Act: -0.0001

Data Index: 917374 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1133656 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.8011. Min Act: -0.0001

Data Index: 1071165 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7989. Min Act: -0.0001

Data Index: 514505 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7706. Min Act: -0.0001

Data Index: 638936 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7516. Min Act: -0.0001

Data Index: 182268 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7672. Min Act: -0.0001

Data Index: 208839 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7647. Min Act: -0.0001

Data Index: 342117 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7690. Min Act: -0.0001

Data Index: 298598 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.9441. Min Range: -0.9441

Max Act: 0.7882. Min Act: -0.0001

Data Index: 647949 (C4 (Web Text))

Max Activating Token Index: 290