Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4254. Min Act: -0.0001

Data Index: 453963 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4340. Min Act: -0.0001

Data Index: 820408 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4159. Min Act: -0.0002

Data Index: 197031 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4044. Min Act: -0.0001

Data Index: 38141 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3694. Min Act: -0.0001

Data Index: 392579 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3617. Min Act: -0.0002

Data Index: 1241290 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3555. Min Act: -0.0001

Data Index: 750744 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3196. Min Act: -0.0001

Data Index: 299916 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3355. Min Act: -0.0001

Data Index: 555748 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3418. Min Act: -0.0001

Data Index: 636927 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3285. Min Act: -0.0002

Data Index: 383406 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2825. Min Act: -0.0001

Data Index: 395590 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3082. Min Act: -0.0002

Data Index: 374572 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3175. Min Act: -0.0002

Data Index: 1126411 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3068. Min Act: -0.0001

Data Index: 75078 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3279. Min Act: -0.0002

Data Index: 1276397 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3221. Min Act: -0.0002

Data Index: 330586 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3033. Min Act: -0.0001

Data Index: 867977 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3042. Min Act: -0.0001

Data Index: 927359 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.2729. Min Act: -0.0001

Data Index: 685867 (C4 (Web Text))

Max Activating Token Index: 684