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

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

Neuron 3121 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: 2.6626. Min Range: -2.6626

Max Act: 2.5298. Min Act: -0.0000

Data Index: 1492689 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.6526. Min Act: -0.0000

Data Index: 1565085 (Python Code)

Max Activating Token Index: 749

Text #2

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.5861. Min Act: -0.0000

Data Index: 1425637 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.6626. Min Act: -0.0000

Data Index: 1569063 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.4618. Min Act: -0.0000

Data Index: 1534875 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3345. Min Act: -0.0000

Data Index: 1551515 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3394. Min Act: -0.0000

Data Index: 1457564 (Python Code)

Max Activating Token Index: 929

Text #7

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.4619. Min Act: -0.0000

Data Index: 1421740 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.4264. Min Act: -0.0000

Data Index: 1392445 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.4464. Min Act: -0.0000

Data Index: 855023 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.2801. Min Act: -0.0000

Data Index: 1374250 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.1448. Min Act: -0.0000

Data Index: 1570742 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.4210. Min Act: -0.0000

Data Index: 1638787 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.1996. Min Act: -0.0000

Data Index: 1605197 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3057. Min Act: -0.0000

Data Index: 1247792 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3035. Min Act: -0.0000

Data Index: 1371979 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.2035. Min Act: -0.0000

Data Index: 1500173 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3699. Min Act: -0.0000

Data Index: 1387102 (Python Code)

Max Activating Token Index: 246

Text #18

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3712. Min Act: -0.0000

Data Index: 1502801 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 2.6626. Min Range: -2.6626

Max Act: 2.3501. Min Act: -0.0000

Data Index: 1480931 (Python Code)

Max Activating Token Index: 967