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

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

Neuron 382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.8585. Min Act: -0.0000

Data Index: 980112 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.9671. Min Act: -0.0000

Data Index: 985704 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.7352. Min Act: -0.0000

Data Index: 445299 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.5869. Min Act: -0.0000

Data Index: 911215 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.5342. Min Act: -0.0000

Data Index: 336414 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.1761. Min Act: -0.0000

Data Index: 467299 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.3868. Min Act: -0.0000

Data Index: 740299 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.0121. Min Act: -0.0000

Data Index: 1096534 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.0718. Min Act: -0.0000

Data Index: 656693 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 2.9671. Min Range: -2.9671

Max Act: 2.0485. Min Act: -0.0000

Data Index: 41056 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.8537. Min Act: -0.0000

Data Index: 594692 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1065685 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.7452. Min Act: -0.0000

Data Index: 578518 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.7516. Min Act: -0.0000

Data Index: 566890 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.6895. Min Act: -0.0000

Data Index: 316888 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.6474. Min Act: -0.0000

Data Index: 362585 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1021136 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.5159. Min Act: -0.0000

Data Index: 573901 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.5769. Min Act: -0.0000

Data Index: 513108 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 2.9671. Min Range: -2.9671

Max Act: 1.4891. Min Act: -0.0000

Data Index: 228225 (C4 (Web Text))

Max Activating Token Index: 460