Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3690 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0002

Data Index: 727344 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0564. Min Act: -0.0002

Data Index: 543744 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0525. Min Act: -0.0002

Data Index: 386459 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0556. Min Act: -0.0002

Data Index: 576830 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0528. Min Act: -0.0002

Data Index: 523084 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0507. Min Act: -0.0002

Data Index: 537427 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1039606 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0491. Min Act: -0.0002

Data Index: 863950 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0474. Min Act: -0.0002

Data Index: 878719 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0462. Min Act: -0.0002

Data Index: 438263 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1269908 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0459. Min Act: -0.0002

Data Index: 606783 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1207631 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1095917 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1164950 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0437. Min Act: -0.0002

Data Index: 551977 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0556. Min Act: -0.0002

Data Index: 489311 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0439. Min Act: -0.0002

Data Index: 445225 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1051200 (C4 (Web Text))

Max Activating Token Index: 146