Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1043 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0002

Data Index: 670918 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0462. Min Act: -0.0002

Data Index: 162090 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1212768 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0465. Min Act: -0.0002

Data Index: 868965 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0442. Min Act: -0.0002

Data Index: 976346 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0437. Min Act: -0.0001

Data Index: 598804 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1078530 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1259116 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1186323 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1085523 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0421. Min Act: -0.0001

Data Index: 885658 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0438. Min Act: -0.0002

Data Index: 654448 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0419. Min Act: -0.0002

Data Index: 629443 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0410. Min Act: -0.0002

Data Index: 535076 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0407. Min Act: -0.0002

Data Index: 235366 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0396. Min Act: -0.0001

Data Index: 596437 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0408. Min Act: -0.0002

Data Index: 133042 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0406. Min Act: -0.0001

Data Index: 855235 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1241899 (C4 (Web Text))

Max Activating Token Index: 286