Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2711 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.8758. Min Act: -0.0000

Data Index: 1184384 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.6656. Min Act: -0.0000

Data Index: 601487 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5257. Min Act: -0.0000

Data Index: 555432 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.5389. Min Act: -0.0000

Data Index: 568622 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3644. Min Act: -0.0001

Data Index: 827742 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3304. Min Act: -0.0000

Data Index: 363179 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.4407. Min Act: -0.0000

Data Index: 576887 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.2027. Min Act: -0.0000

Data Index: 511711 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.3073. Min Act: -0.0001

Data Index: 838556 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1152342 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1586430 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1221096 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1288. Min Act: -0.0001

Data Index: 266536 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1208893 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.8758. Min Range: -1.8758

Max Act: 0.9795. Min Act: -0.0001

Data Index: 1364566 (Python Code)

Max Activating Token Index: 532

Text #15

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1230. Min Act: -0.0001

Data Index: 975626 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.0523. Min Act: -0.0001

Data Index: 775760 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.1247. Min Act: -0.0001

Data Index: 1581537 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.0945. Min Act: -0.0000

Data Index: 170410 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.8758. Min Range: -1.8758

Max Act: 1.0777. Min Act: -0.0000

Data Index: 604506 (C4 (Web Text))

Max Activating Token Index: 566