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

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

Neuron 1655 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0006

Data Index: 400539 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0006

Data Index: 474404 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0428. Min Act: -0.0006

Data Index: 1066780 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0401. Min Act: -0.0006

Data Index: 733705 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0408. Min Act: -0.0006

Data Index: 268607 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0436. Min Act: -0.0006

Data Index: 653763 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1138257 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0428. Min Act: -0.0006

Data Index: 288095 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0407. Min Act: -0.0006

Data Index: 360678 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0414. Min Act: -0.0006

Data Index: 334173 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0396. Min Act: -0.0006

Data Index: 1004179 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0414. Min Act: -0.0006

Data Index: 71440 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0412. Min Act: -0.0006

Data Index: 1141550 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0428. Min Act: -0.0006

Data Index: 374305 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0412. Min Act: -0.0006

Data Index: 50445 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0412. Min Act: -0.0006

Data Index: 1195544 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0402. Min Act: -0.0006

Data Index: 278726 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0412. Min Act: -0.0006

Data Index: 448005 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0415. Min Act: -0.0006

Data Index: 575364 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0400. Min Act: -0.0006

Data Index: 957692 (C4 (Web Text))

Max Activating Token Index: 258