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

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

Neuron 2843 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: 3.3237. Min Range: -3.3237

Max Act: 3.2616. Min Act: -0.0000

Data Index: 452249 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.0850. Min Act: -0.0000

Data Index: 889647 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.3237. Min Act: -0.0000

Data Index: 827245 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.0836. Min Act: -0.0000

Data Index: 1358387 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.2610. Min Act: -0.0000

Data Index: 1231957 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.6487. Min Act: -0.0000

Data Index: 1209856 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.9039. Min Act: -0.0000

Data Index: 309307 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.0305. Min Act: -0.0000

Data Index: 1076441 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.8765. Min Act: -0.0000

Data Index: 343633 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.7498. Min Act: -0.0000

Data Index: 1195375 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 3.3237. Min Range: -3.3237

Max Act: 3.0616. Min Act: -0.0000

Data Index: 96580 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.6835. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.3543. Min Act: -0.0000

Data Index: 1224845 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.2931. Min Act: -0.0000

Data Index: 987453 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.5367. Min Act: -0.0000

Data Index: 455692 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.3328. Min Act: -0.0000

Data Index: 665606 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.2296. Min Act: -0.0000

Data Index: 1244967 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.3193. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.2696. Min Act: -0.0000

Data Index: 359459 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 3.3237. Min Range: -3.3237

Max Act: 2.1326. Min Act: -0.0000

Data Index: 1410591 (Python Code)

Max Activating Token Index: 780