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

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

Neuron 557 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.4920. Min Act: -0.0000

Data Index: 51691 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.3633. Min Act: -0.0000

Data Index: 762768 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.1379. Min Act: -0.0000

Data Index: 292469 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.3745. Min Act: -0.0000

Data Index: 1005217 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.2864. Min Act: -0.0000

Data Index: 835850 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.1526. Min Act: -0.0000

Data Index: 1100254 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.0565. Min Act: -0.0000

Data Index: 349134 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.0200. Min Act: -0.0000

Data Index: 472861 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.9163. Min Act: -0.0000

Data Index: 651812 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 2.4920. Min Range: -2.4920

Max Act: 2.0160. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.9532. Min Act: -0.0000

Data Index: 93930 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.9783. Min Act: -0.0000

Data Index: 313684 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.9030. Min Act: -0.0000

Data Index: 625577 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.9409. Min Act: -0.0000

Data Index: 1016421 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.8998. Min Act: -0.0000

Data Index: 756058 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1000036 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.8555. Min Act: -0.0000

Data Index: 444445 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.8615. Min Act: -0.0000

Data Index: 422947 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.8536. Min Act: -0.0000

Data Index: 8113 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 2.4920. Min Range: -2.4920

Max Act: 1.7179. Min Act: -0.0000

Data Index: 262205 (C4 (Web Text))

Max Activating Token Index: 15