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

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

Neuron 2907 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.6968. Min Range: -3.6968

Max Act: 3.6968. Min Act: -0.0002

Data Index: 545203 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 3.6968. Min Range: -3.6968

Max Act: 3.6325. Min Act: -0.0002

Data Index: 148664 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.9762. Min Act: -0.0002

Data Index: 765128 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.6601. Min Act: -0.0002

Data Index: 1151162 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.4745. Min Act: -0.0002

Data Index: 815654 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.4218. Min Act: -0.0002

Data Index: 307408 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.3643. Min Act: -0.0002

Data Index: 391371 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.4210. Min Act: -0.0002

Data Index: 583352 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.2960. Min Act: -0.0002

Data Index: 327677 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.3324. Min Act: -0.0002

Data Index: 701113 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.3208. Min Act: -0.0002

Data Index: 1217323 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.2631. Min Act: -0.0002

Data Index: 972953 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.1315. Min Act: -0.0002

Data Index: 446997 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.1063. Min Act: -0.0002

Data Index: 837389 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.1491. Min Act: -0.0002

Data Index: 388937 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.1643. Min Act: -0.0002

Data Index: 212265 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.1055. Min Act: -0.0002

Data Index: 618960 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.1383. Min Act: -0.0003

Data Index: 1072850 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.0836. Min Act: -0.0002

Data Index: 512315 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 3.6968. Min Range: -3.6968

Max Act: 2.0931. Min Act: -0.0002

Data Index: 1194629 (C4 (Web Text))

Max Activating Token Index: 935