Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.3204. Min Act: -0.0001

Data Index: 778360 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.3052. Min Act: -0.0001

Data Index: 591000 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2981. Min Act: -0.0001

Data Index: 547052 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2808. Min Act: -0.0001

Data Index: 54248 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2868. Min Act: -0.0001

Data Index: 415988 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1100833 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2717. Min Act: -0.0001

Data Index: 1127391 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1305698 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2548. Min Act: -0.0001

Data Index: 219353 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2715. Min Act: -0.0001

Data Index: 690975 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2670. Min Act: -0.0001

Data Index: 874597 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2537. Min Act: -0.0001

Data Index: 948587 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2441. Min Act: -0.0001

Data Index: 462025 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2414. Min Act: -0.0001

Data Index: 118597 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2414. Min Act: -0.0001

Data Index: 1113516 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1059601 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2291. Min Act: -0.0000

Data Index: 813846 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2379. Min Act: -0.0001

Data Index: 763922 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2354. Min Act: -0.0001

Data Index: 1317154 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.3204. Min Range: -0.3204

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1009046 (C4 (Web Text))

Max Activating Token Index: 435