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

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

Neuron 1734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5556. Min Act: -0.0000

Data Index: 461229 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5772. Min Act: -0.0000

Data Index: 329581 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1151701 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1269317 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1311039 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.5168. Min Act: -0.0000

Data Index: 68762 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4846. Min Act: -0.0000

Data Index: 523535 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4956. Min Act: -0.0000

Data Index: 35387 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4864. Min Act: -0.0000

Data Index: 416520 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4937. Min Act: -0.0000

Data Index: 813955 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1027100 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4569. Min Act: -0.0000

Data Index: 930616 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4559. Min Act: -0.0000

Data Index: 671489 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4799. Min Act: -0.0000

Data Index: 266267 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4480. Min Act: -0.0000

Data Index: 116377 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4472. Min Act: -0.0000

Data Index: 503939 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4521. Min Act: -0.0000

Data Index: 917002 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4393. Min Act: -0.0000

Data Index: 6785 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4334. Min Act: -0.0000

Data Index: 463069 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4428. Min Act: -0.0000

Data Index: 869415 (C4 (Web Text))

Max Activating Token Index: 504