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

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

Neuron 4374 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: 0.3695. Min Range: -0.3695

Max Act: 0.3338. Min Act: -0.0000

Data Index: 930641 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1033827 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1346249 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1156618 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1300335 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2627. Min Act: -0.0000

Data Index: 997348 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1217291 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1043639 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2539. Min Act: -0.0000

Data Index: 949659 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1269752 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1247147 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2455. Min Act: -0.0000

Data Index: 412689 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1192870 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2813. Min Act: -0.0000

Data Index: 463016 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2538. Min Act: -0.0000

Data Index: 190381 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1124969 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1085898 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2450. Min Act: -0.0000

Data Index: 870169 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2268. Min Act: -0.0000

Data Index: 378269 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2439. Min Act: -0.0000

Data Index: 943428 (C4 (Web Text))

Max Activating Token Index: 995