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

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

Neuron 173 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.8129. Min Act: -0.0000

Data Index: 185185 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.5419. Min Act: -0.0000

Data Index: 671870 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.4596. Min Act: -0.0000

Data Index: 604867 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.4627. Min Act: -0.0000

Data Index: 200235 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.2459. Min Act: -0.0000

Data Index: 329189 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.1887. Min Act: -0.0000

Data Index: 1201253 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.5219. Min Act: -0.0000

Data Index: 497403 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.1507. Min Act: -0.0000

Data Index: 260603 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.4941. Min Act: -0.0000

Data Index: 329605 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.2766. Min Act: -0.0000

Data Index: 1107263 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.9547. Min Act: -0.0000

Data Index: 286237 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.9679. Min Act: -0.0000

Data Index: 666045 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.1023. Min Act: -0.0000

Data Index: 1045254 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 4.8129. Min Range: -4.8129

Max Act: 4.0093. Min Act: -0.0000

Data Index: 85335 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.8663. Min Act: -0.0000

Data Index: 1191431 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.9713. Min Act: -0.0000

Data Index: 1322417 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.9547. Min Act: -0.0000

Data Index: 694842 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.9610. Min Act: -0.0000

Data Index: 12404 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.9602. Min Act: -0.0000

Data Index: 888141 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 4.8129. Min Range: -4.8129

Max Act: 3.8541. Min Act: -0.0000

Data Index: 529019 (C4 (Web Text))

Max Activating Token Index: 46