Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3894 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.3917. Min Act: -0.0000

Data Index: 626827 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.3616. Min Act: -0.0000

Data Index: 738222 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.2353. Min Act: -0.0000

Data Index: 476436 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1388135 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1490907 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0157. Min Act: -0.0000

Data Index: 319925 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1058253 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0072. Min Act: -0.0000

Data Index: 663194 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9070. Min Act: -0.0000

Data Index: 366088 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9603. Min Act: -0.0000

Data Index: 917603 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9444. Min Act: -0.0000

Data Index: 802685 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1246392 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9639. Min Act: -0.0000

Data Index: 73996 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.3917. Min Range: -1.3917

Max Act: 1.0149. Min Act: -0.0000

Data Index: 595193 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9307. Min Act: -0.0000

Data Index: 377192 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9363. Min Act: -0.0000

Data Index: 683879 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9589. Min Act: -0.0000

Data Index: 907548 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9862. Min Act: -0.0000

Data Index: 433029 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9187. Min Act: -0.0000

Data Index: 891528 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.3917. Min Range: -1.3917

Max Act: 0.9253. Min Act: -0.0000

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 688