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

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

Neuron 2739 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.3049. Min Act: -0.0000

Data Index: 955732 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1247461 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.2302. Min Act: -0.0001

Data Index: 1435941 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.1040. Min Act: -0.0000

Data Index: 911143 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0201. Min Act: -0.0001

Data Index: 1028925 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1449351 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1084383 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1291072 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0008. Min Act: -0.0000

Data Index: 140703 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0722. Min Act: -0.0001

Data Index: 220510 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9434. Min Act: -0.0000

Data Index: 469959 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0025. Min Act: -0.0001

Data Index: 583879 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9988. Min Act: -0.0001

Data Index: 1171283 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1010318 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0203. Min Act: -0.0001

Data Index: 638161 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0466. Min Act: -0.0000

Data Index: 109092 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0166. Min Act: -0.0000

Data Index: 187273 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.3049. Min Range: -1.3049

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1568751 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9397. Min Act: -0.0000

Data Index: 628322 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.3049. Min Range: -1.3049

Max Act: 0.9398. Min Act: -0.0000

Data Index: 515086 (C4 (Web Text))

Max Activating Token Index: 994