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

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

Neuron 5397 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.3894. Min Act: -0.0000

Data Index: 195307 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1093693 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.2849. Min Act: -0.0000

Data Index: 790679 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.3213. Min Act: -0.0000

Data Index: 810716 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.2863. Min Act: -0.0000

Data Index: 1343856 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1306. Min Act: -0.0000

Data Index: 716508 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.3315. Min Act: -0.0000

Data Index: 487572 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.3611. Min Act: -0.0000

Data Index: 963202 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.2964. Min Act: -0.0000

Data Index: 237942 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.2912. Min Act: -0.0000

Data Index: 237849 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1303. Min Act: -0.0000

Data Index: 453542 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1373. Min Act: -0.0000

Data Index: 984585 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1225018 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1284. Min Act: -0.0000

Data Index: 120448 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1108. Min Act: -0.0000

Data Index: 538091 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0996. Min Act: -0.0000

Data Index: 696143 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1034139 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0067. Min Act: -0.0000

Data Index: 684888 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.0163. Min Act: -0.0000

Data Index: 659496 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.3894. Min Range: -1.3894

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1071349 (C4 (Web Text))

Max Activating Token Index: 818