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

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

Neuron 5408 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.4000. Min Act: -0.0000

Data Index: 612833 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1560864 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1052332 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0803. Min Act: -0.0000

Data Index: 150589 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1360946 (Python Code)

Max Activating Token Index: 547

Text #5

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8950. Min Act: -0.0000

Data Index: 739434 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9527. Min Act: -0.0000

Data Index: 830918 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0250. Min Act: -0.0000

Data Index: 380185 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1111563 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8570. Min Act: -0.0000

Data Index: 571178 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8513. Min Act: -0.0000

Data Index: 882022 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8597. Min Act: -0.0000

Data Index: 413539 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1289936 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8694. Min Act: -0.0000

Data Index: 325524 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1179951 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9464. Min Act: -0.0000

Data Index: 645254 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9039. Min Act: -0.0000

Data Index: 293557 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8884. Min Act: -0.0000

Data Index: 2378 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1346778 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1272417 (C4 (Web Text))

Max Activating Token Index: 238