Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6960. Min Act: -0.0000

Data Index: 327054 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1363965 (Python Code)

Max Activating Token Index: 49

Text #2

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2323. Min Act: -0.0000

Data Index: 131745 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1403331 (Python Code)

Max Activating Token Index: 885

Text #4

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1693. Min Act: -0.0000

Data Index: 42475 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1648. Min Act: -0.0000

Data Index: 389369 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2318. Min Act: -0.0000

Data Index: 243122 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1417. Min Act: -0.0000

Data Index: 242083 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1054371 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1603593 (Python Code)

Max Activating Token Index: 166

Text #10

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1427. Min Act: -0.0000

Data Index: 488005 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1458351 (Python Code)

Max Activating Token Index: 244

Text #12

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1587959 (Python Code)

Max Activating Token Index: 473

Text #13

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0912. Min Act: -0.0000

Data Index: 830281 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0458. Min Act: -0.0000

Data Index: 187438 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1420. Min Act: -0.0000

Data Index: 52425 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1462. Min Act: -0.0000

Data Index: 410941 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0655. Min Act: -0.0000

Data Index: 607399 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0604. Min Act: -0.0000

Data Index: 870743 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0821. Min Act: -0.0000

Data Index: 571335 (C4 (Web Text))

Max Activating Token Index: 785