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

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

Neuron 1078 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0000

Data Index: 484477 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4179. Min Act: -0.0000

Data Index: 535480 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3928. Min Act: 0.0000

Data Index: 1302750 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3902. Min Act: 0.0000

Data Index: 17307 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3506. Min Act: -0.0000

Data Index: 180508 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3243. Min Act: 0.0000

Data Index: 996463 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3475. Min Act: 0.0000

Data Index: 1596599 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1482150 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3334. Min Act: -0.0000

Data Index: 294066 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1328598 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1212857 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3045. Min Act: -0.0000

Data Index: 44907 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1189413 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3080. Min Act: -0.0000

Data Index: 36772 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3264. Min Act: -0.0000

Data Index: 408034 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1186666 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1628135 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3262. Min Act: 0.0000

Data Index: 768593 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2611. Min Act: -0.0000

Data Index: 502793 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2945. Min Act: -0.0000

Data Index: 989049 (C4 (Web Text))

Max Activating Token Index: 395