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

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

Neuron 4893 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2287. Min Range: -2.2287

Max Act: 2.2287. Min Act: -0.0000

Data Index: 757908 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1124084 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.9307. Min Act: -0.0000

Data Index: 1250670 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.7992. Min Act: -0.0000

Data Index: 692918 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.7683. Min Act: -0.0000

Data Index: 666187 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.7165. Min Act: -0.0000

Data Index: 337752 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5791. Min Act: -0.0000

Data Index: 970551 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1195308 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.6130. Min Act: -0.0000

Data Index: 739469 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5094. Min Act: -0.0000

Data Index: 821480 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5960. Min Act: -0.0000

Data Index: 24687 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.6199. Min Act: -0.0000

Data Index: 968875 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5421. Min Act: -0.0000

Data Index: 407857 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5379. Min Act: -0.0000

Data Index: 274855 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.4151. Min Act: -0.0000

Data Index: 513090 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.4136. Min Act: -0.0000

Data Index: 802517 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1078135 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1383282 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.5020. Min Act: -0.0000

Data Index: 869273 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 2.2287. Min Range: -2.2287

Max Act: 1.3780. Min Act: -0.0000

Data Index: 833135 (C4 (Web Text))

Max Activating Token Index: 299