Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0001

Data Index: 456819 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8952. Min Act: -0.0000

Data Index: 153527 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7623. Min Act: -0.0001

Data Index: 736641 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9039. Min Act: -0.0000

Data Index: 520366 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1011707 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8562. Min Act: -0.0001

Data Index: 252387 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8274. Min Act: -0.0000

Data Index: 949113 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1316348 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7684. Min Act: -0.0001

Data Index: 1061099 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7331. Min Act: -0.0001

Data Index: 638106 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7342. Min Act: -0.0000

Data Index: 844262 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7005. Min Act: -0.0001

Data Index: 935265 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1275813 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6863. Min Act: -0.0000

Data Index: 78091 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6763. Min Act: -0.0000

Data Index: 626268 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1199335 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6607. Min Act: -0.0000

Data Index: 452867 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6406. Min Act: -0.0001

Data Index: 57818 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1198271 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.6578. Min Act: -0.0001

Data Index: 389916 (C4 (Web Text))

Max Activating Token Index: 699