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

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

Neuron 3565 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1188581 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4051. Min Act: -0.0000

Data Index: 901076 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3809. Min Act: -0.0000

Data Index: 788680 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3957. Min Act: -0.0000

Data Index: 722103 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3655. Min Act: -0.0000

Data Index: 587028 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3844. Min Act: -0.0000

Data Index: 539553 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1116108 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3690. Min Act: -0.0000

Data Index: 140732 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1223348 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3691. Min Act: -0.0000

Data Index: 943010 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3411. Min Act: -0.0000

Data Index: 520113 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3489. Min Act: -0.0000

Data Index: 243695 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1281994 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3468. Min Act: -0.0000

Data Index: 178874 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3328. Min Act: -0.0000

Data Index: 651577 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3288. Min Act: -0.0000

Data Index: 952157 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3386. Min Act: -0.0000

Data Index: 210245 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3259. Min Act: -0.0000

Data Index: 276870 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1233595 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3198. Min Act: -0.0000

Data Index: 476741 (C4 (Web Text))

Max Activating Token Index: 802