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

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

Neuron 4962 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.2079. Min Act: -0.0000

Data Index: 65881 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1071575 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.1726. Min Act: -0.0000

Data Index: 490518 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0880. Min Act: -0.0000

Data Index: 144473 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1053940 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.1146. Min Act: -0.0000

Data Index: 576131 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1315961 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0328. Min Act: -0.0000

Data Index: 776401 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9471. Min Act: 0.0000

Data Index: 787436 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8173. Min Act: -0.0000

Data Index: 938024 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8958. Min Act: -0.0000

Data Index: 160497 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9702. Min Act: -0.0000

Data Index: 379822 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8776. Min Act: -0.0000

Data Index: 560880 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1286654 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8838. Min Act: -0.0000

Data Index: 782077 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8956. Min Act: -0.0000

Data Index: 239012 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9082. Min Act: -0.0000

Data Index: 13024 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9100. Min Act: -0.0000

Data Index: 100686 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1128243 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.8905. Min Act: -0.0000

Data Index: 524256 (C4 (Web Text))

Max Activating Token Index: 605