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

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

Neuron 410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.8020. Min Act: -0.0000

Data Index: 61260 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 3.0181. Min Range: -3.0181

Max Act: 3.0181. Min Act: -0.0000

Data Index: 1285941 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.9758. Min Act: -0.0000

Data Index: 372837 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.6124. Min Act: -0.0000

Data Index: 726723 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.7422. Min Act: -0.0000

Data Index: 680961 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.6052. Min Act: -0.0000

Data Index: 1248323 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.4786. Min Act: -0.0000

Data Index: 190549 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.7427. Min Act: -0.0000

Data Index: 778135 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.7125. Min Act: -0.0000

Data Index: 117482 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.7080. Min Act: -0.0000

Data Index: 470797 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.4362. Min Act: -0.0000

Data Index: 86174 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.4437. Min Act: -0.0000

Data Index: 322500 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.5598. Min Act: -0.0000

Data Index: 127572 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.5499. Min Act: -0.0000

Data Index: 1137459 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.5259. Min Act: -0.0000

Data Index: 1042110 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.5016. Min Act: -0.0000

Data Index: 672216 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.4874. Min Act: -0.0000

Data Index: 1070374 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.4888. Min Act: -0.0000

Data Index: 446708 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.3441. Min Act: -0.0000

Data Index: 41235 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.0181. Min Range: -3.0181

Max Act: 2.5936. Min Act: -0.0000

Data Index: 513202 (C4 (Web Text))

Max Activating Token Index: 466