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

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

Neuron 3125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1565. Min Range: -2.1565

Max Act: 2.0986. Min Act: -0.0000

Data Index: 298867 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 2.1565. Min Range: -2.1565

Max Act: 2.1565. Min Act: -0.0000

Data Index: 104024 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.1565. Min Range: -2.1565

Max Act: 2.1349. Min Act: -0.0000

Data Index: 974464 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 2.1565. Min Range: -2.1565

Max Act: 2.0956. Min Act: -0.0000

Data Index: 459863 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.9807. Min Act: -0.0000

Data Index: 253426 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.9366. Min Act: -0.0000

Data Index: 69707 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.7590. Min Act: -0.0000

Data Index: 142536 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.7369. Min Act: -0.0000

Data Index: 688332 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.7028. Min Act: -0.0000

Data Index: 652337 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.7057. Min Act: -0.0000

Data Index: 675066 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.8895. Min Act: -0.0000

Data Index: 965209 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.5544. Min Act: -0.0000

Data Index: 925344 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.6247. Min Act: -0.0000

Data Index: 350789 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.5337. Min Act: -0.0000

Data Index: 564492 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.5849. Min Act: -0.0000

Data Index: 872117 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.5140. Min Act: -0.0000

Data Index: 536022 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.4900. Min Act: -0.0000

Data Index: 681017 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.4914. Min Act: -0.0000

Data Index: 1168705 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.4754. Min Act: -0.0000

Data Index: 879842 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 2.1565. Min Range: -2.1565

Max Act: 1.5662. Min Act: -0.0000

Data Index: 106876 (C4 (Web Text))

Max Activating Token Index: 1011