Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4643. Min Act: -0.0001

Data Index: 438764 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4361. Min Act: -0.0001

Data Index: 217879 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3703. Min Act: -0.0000

Data Index: 354432 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3752. Min Act: -0.0001

Data Index: 557838 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3687. Min Act: -0.0001

Data Index: 260954 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3521. Min Act: -0.0001

Data Index: 301118 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3628. Min Act: -0.0000

Data Index: 949014 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1209735 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3552. Min Act: -0.0001

Data Index: 517003 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3501. Min Act: -0.0001

Data Index: 374585 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3494. Min Act: -0.0001

Data Index: 35355 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3427. Min Act: -0.0001

Data Index: 117184 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3451. Min Act: -0.0000

Data Index: 581082 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3417. Min Act: -0.0001

Data Index: 839334 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3513. Min Act: -0.0001

Data Index: 811962 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3358. Min Act: -0.0001

Data Index: 797663 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3394. Min Act: -0.0001

Data Index: 498155 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3274. Min Act: -0.0001

Data Index: 921795 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3133. Min Act: 0.0000

Data Index: 544177 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3142. Min Act: -0.0001

Data Index: 773604 (C4 (Web Text))

Max Activating Token Index: 162