Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6924. Min Act: -0.0001

Data Index: 264047 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.7130. Min Act: -0.0001

Data Index: 47258 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1234397 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.7041. Min Act: -0.0001

Data Index: 692136 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6544. Min Act: -0.0001

Data Index: 549891 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5900. Min Act: -0.0001

Data Index: 959175 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5347. Min Act: -0.0001

Data Index: 294630 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1455374 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6082. Min Act: -0.0001

Data Index: 856764 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6741. Min Act: -0.0001

Data Index: 159998 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5752. Min Act: -0.0001

Data Index: 1372226 (Python Code)

Max Activating Token Index: 431

Text #11

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5650. Min Act: -0.0001

Data Index: 400185 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5513. Min Act: -0.0001

Data Index: 75771 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5691. Min Act: -0.0001

Data Index: 27389 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5830. Min Act: -0.0001

Data Index: 1283735 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6217. Min Act: -0.0001

Data Index: 235647 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4980. Min Act: -0.0001

Data Index: 621488 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5005. Min Act: -0.0001

Data Index: 848949 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5795. Min Act: -0.0001

Data Index: 550122 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4997. Min Act: -0.0001

Data Index: 1476483 (Python Code)

Max Activating Token Index: 769