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

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

Neuron 1531 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.6640. Min Act: -0.0000

Data Index: 72851 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.2743. Min Act: -0.0000

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.3815. Min Act: -0.0000

Data Index: 1228802 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.3376. Min Act: -0.0000

Data Index: 1302443 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.1055. Min Act: -0.0000

Data Index: 1070402 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.0384. Min Act: -0.0000

Data Index: 816605 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.9318. Min Act: -0.0000

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 4.6640. Min Range: -4.6640

Max Act: 4.0692. Min Act: -0.0000

Data Index: 200543 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.8530. Min Act: -0.0000

Data Index: 601013 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.8512. Min Act: -0.0000

Data Index: 1077764 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.7858. Min Act: -0.0000

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.7843. Min Act: -0.0000

Data Index: 240319 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.6667. Min Act: -0.0000

Data Index: 947540 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.4952. Min Act: -0.0000

Data Index: 342025 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.6028. Min Act: -0.0000

Data Index: 149120 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.5488. Min Act: -0.0000

Data Index: 1066151 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.5532. Min Act: -0.0000

Data Index: 881814 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.4998. Min Act: -0.0000

Data Index: 380562 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.3229. Min Act: -0.0000

Data Index: 1055934 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 4.6640. Min Range: -4.6640

Max Act: 3.5555. Min Act: -0.0000

Data Index: 33753 (C4 (Web Text))

Max Activating Token Index: 139