Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3583 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.3177. Min Act: -0.0001

Data Index: 703904 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2843. Min Act: -0.0000

Data Index: 67142 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2672. Min Act: -0.0001

Data Index: 134819 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2837. Min Act: -0.0001

Data Index: 23152 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2794. Min Act: -0.0000

Data Index: 224230 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2693. Min Act: -0.0001

Data Index: 411282 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2717. Min Act: -0.0001

Data Index: 169308 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2798. Min Act: -0.0000

Data Index: 791627 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2668. Min Act: -0.0001

Data Index: 888409 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2681. Min Act: -0.0001

Data Index: 420297 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2657. Min Act: 0.0000

Data Index: 1220110 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2556. Min Act: -0.0001

Data Index: 28342 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1136308 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1150182 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2514. Min Act: -0.0001

Data Index: 987563 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2493. Min Act: -0.0001

Data Index: 247041 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2573. Min Act: -0.0000

Data Index: 663424 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1304674 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2638. Min Act: -0.0000

Data Index: 986988 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.3177. Min Range: -0.3177

Max Act: 0.2452. Min Act: -0.0001

Data Index: 492535 (C4 (Web Text))

Max Activating Token Index: 963