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

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

Neuron 4330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.4512. Min Act: -0.0000

Data Index: 592817 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.4577. Min Act: -0.0000

Data Index: 200263 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.4076. Min Act: -0.0000

Data Index: 122768 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1350741 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3495. Min Act: -0.0000

Data Index: 602394 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3424. Min Act: -0.0000

Data Index: 391361 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1268169 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1188341 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3309. Min Act: -0.0000

Data Index: 910133 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3355. Min Act: -0.0000

Data Index: 537507 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1021591 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1307663 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1061944 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3155. Min Act: -0.0000

Data Index: 834619 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3251. Min Act: -0.0000

Data Index: 92713 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3039. Min Act: -0.0000

Data Index: 805048 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3125. Min Act: -0.0000

Data Index: 41984 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3089. Min Act: -0.0000

Data Index: 450133 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3127. Min Act: -0.0000

Data Index: 935137 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.4577. Min Range: -0.4577

Max Act: 0.3118. Min Act: -0.0000

Data Index: 676134 (C4 (Web Text))

Max Activating Token Index: 277