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

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

Neuron 4568 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: 1.0568. Min Range: -1.0568

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1182549 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9925. Min Act: -0.0000

Data Index: 532353 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1097020 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9232. Min Act: -0.0000

Data Index: 792054 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9193. Min Act: -0.0000

Data Index: 613337 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1348220 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.8561. Min Act: -0.0000

Data Index: 46114 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.8387. Min Act: -0.0000

Data Index: 32647 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7924. Min Act: -0.0000

Data Index: 441571 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1222571 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7563. Min Act: -0.0000

Data Index: 382924 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1224655 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1293145 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7402. Min Act: -0.0000

Data Index: 190693 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7492. Min Act: -0.0000

Data Index: 989620 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7452. Min Act: -0.0000

Data Index: 199487 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7451. Min Act: -0.0000

Data Index: 534436 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7241. Min Act: -0.0000

Data Index: 221482 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1010432 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.7364. Min Act: -0.0000

Data Index: 220237 (C4 (Web Text))

Max Activating Token Index: 87