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

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

Neuron 4909 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5624. Min Act: -0.0001

Data Index: 762246 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5218. Min Act: -0.0001

Data Index: 668136 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5099. Min Act: -0.0001

Data Index: 519003 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5104. Min Act: -0.0001

Data Index: 1270191 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4469. Min Act: -0.0001

Data Index: 57490 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4312. Min Act: -0.0001

Data Index: 488923 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4530. Min Act: -0.0001

Data Index: 829654 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4459. Min Act: -0.0001

Data Index: 349079 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3472. Min Act: -0.0001

Data Index: 776952 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3659. Min Act: -0.0001

Data Index: 1116730 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1285609 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3601. Min Act: -0.0000

Data Index: 996686 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3233. Min Act: -0.0001

Data Index: 349800 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3330. Min Act: -0.0001

Data Index: 137322 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3038. Min Act: -0.0000

Data Index: 998483 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3145. Min Act: -0.0001

Data Index: 1353570 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2757. Min Act: -0.0001

Data Index: 372610 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.3083. Min Act: -0.0001

Data Index: 192722 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2924. Min Act: -0.0001

Data Index: 694584 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.2716. Min Act: -0.0000

Data Index: 355947 (C4 (Web Text))

Max Activating Token Index: 461