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

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

Neuron 3108 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4721. Min Act: -0.0000

Data Index: 136385 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4168. Min Act: -0.0000

Data Index: 634078 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1325750 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4297. Min Act: -0.0000

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1317238 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4281. Min Act: -0.0000

Data Index: 959188 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4301. Min Act: -0.0000

Data Index: 279850 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1060357 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3803. Min Act: -0.0000

Data Index: 889304 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4170. Min Act: -0.0000

Data Index: 976615 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3904. Min Act: -0.0000

Data Index: 885074 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4020. Min Act: -0.0000

Data Index: 63691 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1033667 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4109. Min Act: -0.0000

Data Index: 770722 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3859. Min Act: -0.0000

Data Index: 294686 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3793. Min Act: -0.0000

Data Index: 415909 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1167225 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3950. Min Act: -0.0000

Data Index: 852901 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4072. Min Act: -0.0000

Data Index: 611559 (C4 (Web Text))

Max Activating Token Index: 759