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

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

Neuron 2196 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: 3.8180. Min Range: -3.8180

Max Act: 3.8180. Min Act: -0.0000

Data Index: 1645401 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 3.8180. Min Range: -3.8180

Max Act: 3.1216. Min Act: -0.0000

Data Index: 1440647 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 3.8180. Min Range: -3.8180

Max Act: 3.1250. Min Act: -0.0000

Data Index: 1633721 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 3.8180. Min Range: -3.8180

Max Act: 3.2726. Min Act: -0.0000

Data Index: 1423151 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 3.8180. Min Range: -3.8180

Max Act: 3.1296. Min Act: -0.0000

Data Index: 1420215 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.9631. Min Act: -0.0000

Data Index: 1464650 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 3.8180. Min Range: -3.8180

Max Act: 3.1151. Min Act: -0.0000

Data Index: 1618281 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 3.8180. Min Range: -3.8180

Max Act: 3.0741. Min Act: -0.0000

Data Index: 1537756 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.7973. Min Act: -0.0000

Data Index: 1520895 (Python Code)

Max Activating Token Index: 885

Text #9

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.9505. Min Act: -0.0000

Data Index: 1468522 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.7881. Min Act: -0.0000

Data Index: 1612895 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.6550. Min Act: -0.0000

Data Index: 1618242 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.7449. Min Act: -0.0000

Data Index: 1408347 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.7039. Min Act: -0.0000

Data Index: 1404163 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.6942. Min Act: -0.0000

Data Index: 1581648 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.5335. Min Act: -0.0000

Data Index: 1458487 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.8269. Min Act: -0.0000

Data Index: 1365508 (Python Code)

Max Activating Token Index: 956

Text #17

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.4885. Min Act: -0.0000

Data Index: 1616207 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.4920. Min Act: -0.0000

Data Index: 1525129 (Python Code)

Max Activating Token Index: 465

Text #19

Max Range: 3.8180. Min Range: -3.8180

Max Act: 2.7253. Min Act: -0.0000

Data Index: 1605724 (Python Code)

Max Activating Token Index: 837