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

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

Neuron 1303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.6469. Min Act: -0.0000

Data Index: 1001334 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 2.0426. Min Range: -2.0426

Max Act: 2.0426. Min Act: -0.0000

Data Index: 193005 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.5975. Min Act: -0.0000

Data Index: 350824 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.6199. Min Act: -0.0000

Data Index: 834009 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.4425. Min Act: -0.0000

Data Index: 969829 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1049043 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.5052. Min Act: -0.0000

Data Index: 351045 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1051258 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.4392. Min Act: -0.0000

Data Index: 932651 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1035996 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.4044. Min Act: -0.0000

Data Index: 782638 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.6229. Min Act: -0.0000

Data Index: 1118609 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3380. Min Act: -0.0000

Data Index: 491320 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3264. Min Act: -0.0000

Data Index: 523179 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3365. Min Act: -0.0000

Data Index: 458459 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1331541 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3679. Min Act: -0.0000

Data Index: 984374 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.2906. Min Act: -0.0000

Data Index: 460632 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.3121. Min Act: -0.0000

Data Index: 683699 (C4 (Web Text))

Max Activating Token Index: 55