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

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

Neuron 1442 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5091. Min Range: -3.5091

Max Act: 3.5091. Min Act: -0.0000

Data Index: 1603288 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 3.5091. Min Range: -3.5091

Max Act: 3.1711. Min Act: -0.0000

Data Index: 1644751 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 3.5091. Min Range: -3.5091

Max Act: 3.2477. Min Act: -0.0000

Data Index: 1363778 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 3.5091. Min Range: -3.5091

Max Act: 3.4024. Min Act: -0.0000

Data Index: 1516847 (Python Code)

Max Activating Token Index: 789

Text #4

Max Range: 3.5091. Min Range: -3.5091

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1406783 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 3.5091. Min Range: -3.5091

Max Act: 3.4553. Min Act: -0.0000

Data Index: 1595910 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.7979. Min Act: -0.0000

Data Index: 1524141 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.6942. Min Act: -0.0000

Data Index: 1407438 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.8569. Min Act: -0.0000

Data Index: 1629075 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.3981. Min Act: -0.0000

Data Index: 1630300 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.9158. Min Act: -0.0000

Data Index: 1545017 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.9028. Min Act: -0.0000

Data Index: 1514128 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.8805. Min Act: -0.0000

Data Index: 1579128 (Python Code)

Max Activating Token Index: 456

Text #13

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.7340. Min Act: -0.0000

Data Index: 1615476 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1554033 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.8616. Min Act: -0.0000

Data Index: 1441840 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.5746. Min Act: -0.0000

Data Index: 1583933 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.8531. Min Act: -0.0000

Data Index: 1645095 (Python Code)

Max Activating Token Index: 794

Text #18

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.8447. Min Act: -0.0000

Data Index: 1379637 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 3.5091. Min Range: -3.5091

Max Act: 2.5356. Min Act: -0.0000

Data Index: 1624564 (Python Code)

Max Activating Token Index: 785