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

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

Neuron 549 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4598. Min Range: -1.4598

Max Act: 1.4598. Min Act: -0.0000

Data Index: 208081 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.4598. Min Range: -1.4598

Max Act: 1.0826. Min Act: -0.0000

Data Index: 956559 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.8837. Min Act: -0.0000

Data Index: 432926 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.8726. Min Act: -0.0000

Data Index: 429677 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.8526. Min Act: -0.0000

Data Index: 789325 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1258224 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1238309 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.6943. Min Act: -0.0000

Data Index: 315367 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.7343. Min Act: -0.0000

Data Index: 154193 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.6738. Min Act: -0.0000

Data Index: 715316 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1254471 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1266341 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.5486. Min Act: -0.0000

Data Index: 22653 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.6310. Min Act: -0.0000

Data Index: 948918 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1126276 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1359006 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.5871. Min Act: -0.0000

Data Index: 700542 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.6022. Min Act: -0.0000

Data Index: 415144 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1144947 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.4598. Min Range: -1.4598

Max Act: 0.5443. Min Act: -0.0000

Data Index: 423299 (C4 (Web Text))

Max Activating Token Index: 826