Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 255 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.2434. Min Act: -0.0001

Data Index: 966976 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.1044. Min Act: -0.0001

Data Index: 1196155 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1193391 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.0787. Min Act: -0.0001

Data Index: 615331 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.1060. Min Act: -0.0001

Data Index: 1310276 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.0808. Min Act: -0.0001

Data Index: 201241 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.0739. Min Act: -0.0001

Data Index: 317915 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9369. Min Act: -0.0001

Data Index: 682582 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9882. Min Act: -0.0001

Data Index: 837261 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9491. Min Act: -0.0001

Data Index: 229699 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9517. Min Act: -0.0001

Data Index: 626711 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9515. Min Act: -0.0001

Data Index: 1062719 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9830. Min Act: -0.0001

Data Index: 667209 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9925. Min Act: -0.0001

Data Index: 1327307 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9375. Min Act: -0.0001

Data Index: 561336 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 1.2434. Min Range: -1.2434

Max Act: 1.0186. Min Act: -0.0001

Data Index: 1102376 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9734. Min Act: -0.0001

Data Index: 734062 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.7458. Min Act: -0.0001

Data Index: 351739 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.9682. Min Act: -0.0001

Data Index: 871656 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.2434. Min Range: -1.2434

Max Act: 0.8625. Min Act: -0.0001

Data Index: 320977 (C4 (Web Text))

Max Activating Token Index: 140