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

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

Neuron 2211 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.6053. Min Act: -0.0000

Data Index: 677308 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5755. Min Act: -0.0000

Data Index: 628329 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5936. Min Act: -0.0000

Data Index: 193381 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5727. Min Act: -0.0000

Data Index: 898614 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1124709 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5517. Min Act: -0.0000

Data Index: 686253 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5552. Min Act: 0.0000

Data Index: 1133629 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1134278 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4925. Min Act: -0.0000

Data Index: 32601 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1058391 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4831. Min Act: -0.0000

Data Index: 261690 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4950. Min Act: -0.0000

Data Index: 910468 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4814. Min Act: 0.0000

Data Index: 253546 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4883. Min Act: -0.0000

Data Index: 468979 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4877. Min Act: -0.0000

Data Index: 399848 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4815. Min Act: -0.0000

Data Index: 654763 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4653. Min Act: -0.0000

Data Index: 778789 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4714. Min Act: -0.0000

Data Index: 356273 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4525. Min Act: -0.0000

Data Index: 87864 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.6053. Min Range: -0.6053

Max Act: 0.4473. Min Act: -0.0000

Data Index: 182308 (C4 (Web Text))

Max Activating Token Index: 766